Security
Plugin
clawsec
A complete security skill suite for OpenClaw, Hermes, PicoClaw and NanoClaw agents (and variants). Protect your SOUL.md (etc') with drift detection, live security recommendations, automated audits, and skill integrity verification. All from one installable suite.
Plugin Signal82/100Strong
maintained100
capable59
documented100
adopted65
Install
$ npx -y skills add prompt-security/clawsec --agent claude-code
Run the curl in your terminal, the rest in Claude Code.
Stats
1,082
Stars
114
Forks
Active
Maintenance
JavaScript
Language
AGPL-3.0
License
7h ago
Last commit
6mo ago
Created
Repo: prompt-security/clawsec
In this plugin
- claw-release
- clawsec-clawhub-checker
- clawsec-feed
- clawsec-nanoclaw
- clawsec-scanner
- clawsec-suite
- clawtributor
- hermes-attestation-guardian
- hermes-traffic-guardian
- nanoclaw-traffic-guardian
- openclaw-audit-watchdog
- openclaw-traffic-guardian
- picoclaw-security-guardian
- picoclaw-self-pen-testing
- picoclaw-traffic-guardian
- soul-guardian
What's inside
Skills
16/claw-releaseRelease automation for Claw skills and website. Guides through version bumping, tagging, and release verification./clawsec-clawhub-checkerClawHub reputation checker for clawsec-suite. Adds a standalone reputation gate before guarded skill installation./clawsec-feedSecurity advisory feed package for OpenClaw-related threats and vulnerabilities. The upstream feed is updated daily; local automation is handled by clawsec-suite or the operator./clawsec-nanoclawUse when checking for security vulnerabilities in NanoClaw skills, before installing new skills, or when asked about security advisories affecting the bot/clawsec-scannerAutomated vulnerability scanner for agent platforms. Performs dependency scanning (npm audit, pip-audit), multi-database CVE lookup (OSV, NVD, GitHub Advisory), SAST analysis (Semgrep, Bandit), and agent-specific static hook inspection for OpenClaw hooks./clawsec-suiteClawSec suite manager with embedded advisory-feed monitoring, cryptographic signature verification, approval-gated malicious-skill response, and guided setup for additional security skills.
Show all 16 skillsShow fewer
/clawtributorHarness-neutral community incident reporting for AI agents. Contribute to collective security by reporting threats./hermes-attestation-guardianHermes-only runtime security attestation and drift detection skill for operator-managed Hermes infrastructure./hermes-traffic-guardianHermes runtime traffic monitoring baseline for opt-in proxy inspection, egress detection, and attestation-aware traffic posture./nanoclaw-traffic-guardianNanoClaw runtime traffic monitoring baseline for host-side proxy inspection with container-safe MCP and IPC status surfaces./openclaw-audit-watchdogOptional email copy destination./openclaw-traffic-guardianOpenClaw runtime traffic monitoring baseline for opt-in HTTP/HTTPS proxy inspection, egress detection, inbound injection detection, and social-account policy review./picoclaw-security-guardianPicoclaw security posture skill with advisory awareness, configuration drift detection, and supply-chain verification guidance./picoclaw-self-pen-testingPicoclaw-only local posture-review skill focused on read-only findings and safe operator remediation guidance./picoclaw-traffic-guardianPicoclaw runtime traffic monitoring baseline for lightweight AI gateway proxy inspection, egress detection, and posture integration./soul-guardianDrift detection + baseline integrity guard for agent workspace files with automatic alerting support
README
1ClawSec is an AGPL collection of security skills and signed advisory intelligence for AI agent runtimes. It helps operators verify skill artifacts, detect configuration drift, audit agent environments, and approval-gate risky installs across OpenClaw, NanoClaw, Hermes, and Picoclaw.
Install the OpenClaw suite
The OpenClaw entry point is clawsec-suite. Adding the package and activating its persistent hook are separate, reviewable steps.
1. Add the suite
npx skills add prompt-security/clawsec --skill clawsec-suite -a openclaw --global -y
This installs the suite with its signed advisory trust set, heartbeat workflow, guarded installer, and setup scripts. Optional protections remain separate packages that the suite discovers from the published catalog.
2. Review and enable the advisory hook
SUITE_DIR="${INSTALL_ROOT:-$HOME/.openclaw/skills}/clawsec-suite"
node "$SUITE_DIR/scripts/setup_advisory_hook.mjs"
The setup script prints its preflight before it changes persistent OpenClaw configuration. After it succeeds, restart the OpenClaw gateway and run /new once to trigger the first advisory scan.
To see the current optional protections:
node "$SUITE_DIR/scripts/discover_skill_catalog.mjs"
Installing for someone else? Ask their agent to install
clawsec-suitewith the command above, show the hook preflight, and wait for approval before enabling the hook or optional cron job.
For bash and zsh, keep home variables expandable:
export INSTALL_ROOT="$HOME/.openclaw/skills"
Do not single-quote paths that contain $HOME. In PowerShell, build the path explicitly:
$env:INSTALL_ROOT = Join-Path $HOME ".openclaw\skills"
node "$env:INSTALL_ROOT\clawsec-suite\scripts\setup_advisory_hook.mjs"
POSIX .sh workflows require WSL or Git Bash on Windows.
See it work
Detect and respond to agent-file drift
The soul-guardian demo changes a protected agent file, detects the mismatch, and walks through the response.
How ClawSec protects an agent
| Protection layer | What it does |
|---|---|
| Signed intelligence | Verifies the advisory feed and checksum manifest before matching published risk against installed skills. |
| Guarded installs | Stops on advisory matches and requires a second, explicit confirmation before a risky install can continue. |
| Integrity and drift | Gives platform-specific skills baselines for critical files, configuration, attestations, and release artifacts. |
| Audits and reporting | Provides focused audit, posture, self-test, and community-reporting packages where the platform contract supports them. |
ClawSec recommends and gates actions; destructive removal and install overrides remain approval-controlled.
Platform entry points
- OpenClaw β start with
clawsec-suitefor signed advisory monitoring and guarded installs, then discover separate drift and audit protections. - NanoClaw β use
clawsec-nanoclawfor NanoClaw-specific advisory, integrity, verification, and security-tool workflows. - Hermes β use
hermes-attestation-guardianfor signed advisory checks, guarded verification, deterministic attestations, and baseline drift detection. - Picoclaw β use
picoclaw-security-guardianfor posture, advisory, drift, and release-artifact checks. Self-pen testing is a separate opt-in package.
The
*-traffic-guardiandirectories are specification baselines for platform builders. They are not shipped runtime proxies today.
Browse every package in the live skill catalog or the repositoryβs skills/ directory.
Skill feature matrix
The full package comparison is preserved in the wiki, including shipped, limited, and specification-only coverage.
Compare every skill in the feature matrix β
Query the signed advisory channel
The consolidated feed can contain relevant NVD CVEs, approved community reports, and provisional GitHub advisories that do not yet have CVE identifiers.
curl -fsSL https://clawsec.prompt.security/advisories/feed.json \
| jq '.advisories[] | select(.severity == "critical" or .severity == "high")'
Trust material lives beside the feed:
The legacy /releases/latest/download/feed.json endpoint remains a compatibility mirror. New consumers should use the canonical /advisories/feed.json endpoint.
Build, test, and contribute
Run the web catalog locally:
npm install
npm run dev
Run the repositoryβs local quality gate before pushing:
./scripts/prepare-to-push.sh
Validate a skill package directly:
python utils/validate_skill.py skills/clawsec-feed
Start with these references:
The source of truth for project documentation is wiki/. GitHub Wiki pages and LLM-ready exports are generated from those files.
Translations
English Β· Deutsch Β· EspaΓ±ol Β· FranΓ§ais Β· ζ₯ζ¬θͺ Β· νκ΅μ΄
Localized wiki indexes: DE Β· ES Β· FR Β· JA Β· KO Β· EN
License
ClawSec source code is licensed under GNU AGPL-3.0-or-later. See LICENSE. Files under font/ have separate license terms and are not used by the README artwork.
File tree
541prompt-security/clawsecView on GitHub
.claude-plugin/
marketplace.json
.gitattributes
.github/
actions/
sign-and-verify/
action.yml
clawhub-cli/
package-lock.json
package.json
codeql/
codeql-config.yml
dependabot.yml
ISSUE_TEMPLATE/
bug_report.md
feature_request.md
security_incident_report.md
PULL_REQUEST_TEMPLATE.md
requirements-lint-python.txt
workflows/
archive-traffic.yml
ci.yml
codeql.yml
community-advisory.yml
deploy-pages.yml
i18n-qa.yml
pages-verify.yml
poll-ghsa-without-cve.yml
poll-nvd-cves.yml
scorecard.yml
skill-release.yml
wiki-export-verify.yml
wiki-sync.yml
.gitignore
advisories/
feed-signing-public.pem
feed.json
feed.json.sig
ghsa-without-cve.json
ghsa-without-cve.json.sig
AGENTS.md
App.tsx
assets/
readme/
hero-de.webp
hero-es.webp
hero-fr.webp
hero-ja.webp
hero-ko.webp
hero.webp
source/
generate-localized-hero-svgs.mjs
hero-copy.json
hero-layout-de.svg
hero-layout-es.svg
hero-layout-fr.svg
hero-layout-ja.svg
hero-layout-ko.svg
hero-layout.svg
hero-manifest.mjs
hero-manifest.test.mjs
README.md
verify-localized-heroes.mjs
CITATION.cff
CLAUDE.md
clawsec-signing-public.pem
CODE_OF_CONDUCT.md
components/
AdvisoryCard.tsx
AdvisoryPlatformBadge.tsx
CodeBlock.tsx
Footer.tsx
Header.tsx
Layout.tsx
LobsterBackground.tsx
SkillCard.tsx
constants.ts
CONTRIBUTING.md
eslint.config.js
font/
Prometo_Trial_Bd.ttf
Prometo_Trial_BdIt.ttf
Prometo_Trial_Blk.ttf
Prometo_Trial_BlkIt.ttf
Prometo_Trial_It.ttf
Prometo_Trial_Lt.ttf
Prometo_Trial_LtIt.ttf
Prometo_Trial_Md.ttf
Prometo_Trial_MdIt.ttf
Prometo_Trial_Rg.ttf
Prometo_Trial_Th.ttf
Prometo_Trial_ThIt.ttf
Prometo_Trial_XBd.ttf
Prometo_Trial_XBdIt.ttf
README.md
img/
Black+Color.png
prompt-icon.svg
index.html
index.tsx
LICENSE
metadata.json
package-lock.json
package.json
pages/
AdvisoryDetail.tsx
Checksums.tsx
FeedSetup.tsx
Home.tsx
ProductDemo.tsx
SkillDetail.tsx
SkillsCatalog.tsx
WikiBrowser.tsx
public/
img/
favicon.ico
mascot.png
prompt_line.svg
video/
install-demo-poster.jpg
install-demo-preview.gif
install-demo.mp4
soul-guardian-demo-poster.jpg
soul-guardian-demo-preview.gif
soul-guardian-demo.mp4
pyproject.toml
README.de.md
README.es.md
README.fr.md
README.ja.md
README.ko.md
README.md
scripts/
archive-github-traffic.mjs
backfill-exploitability.sh
build-github-wiki-export.mjs
ci/
advisory_pages_artifacts.mjs
clawhub_release_package.mjs
enrich_exploitability.sh
generate_skill_release_trust_packet.mjs
guard_clawhub_slug_owner.sh
install_clawhub_cli.sh
patch_clawhub_publish_payload.mjs
patch_clawhub_trust_extensions.mjs
release_path_policy.mjs
repair_stale_exploitability.mjs
resolve_clawhub_slug.mjs
semver_increment.mjs
simulate_skill_tag_release.mjs
skill_platforms.mjs
test_verify_skill_release_import_closure.py
validate_skill_install_docs.mjs
verify_signing_key_consistency.sh
verify_skill_release_import_closure.py
feed-utils.sh
fixtures/
advisory-consumer-semver.json
generate-wiki-llms.mjs
ghsa-without-cve-feed.mjs
i18n/
bootstrap_language_from_en.py
fill_missing_translations_argos.py
link_check.py
qa_check.py
test_fill_missing_translations_argos.py
test_qa_check.py
populate-local-feed.sh
populate-local-skills.sh
populate-local-wiki.sh
prepare-to-push.sh
release-skill.sh
test-advisory-consumer-compatibility.mjs
test-advisory-mirror-propagation.mjs
test-deploy-pages-checksums.mjs
test-ghsa-poll-workflow.mjs
test-ghsa-without-cve-feed.mjs
test-github-traffic-archive.mjs
test-nvd-exploitability-repair.mjs
test-nvd-ghsa-consolidation-workflow.mjs
test-nvd-ghsa-pipeline-dry-run.mjs
test-skill-clawhub-slug.mjs
test-skill-clawhub-trust-extensions.mjs
test-skill-install-docs.mjs
test-skill-release-path-policy.mjs
test-skill-release-semver.mjs
test-skill-release-workflow.mjs
test-skill-tag-release-simulation.mjs
test-skill-trust-packet.mjs
test-wiki-sync-export.mjs
validate-release-links.sh
SECURITY.md
skills/
claw-release/
.clawhubignore
CHANGELOG.md
README.md
skill.json
SKILL.md
clawsec-clawhub-checker/
.clawhubignore
CHANGELOG.md
hooks/
clawsec-advisory-guardian/
lib/
reputation.mjs
README.md
scripts/
check_clawhub_reputation.mjs
enhanced_guarded_install.mjs
setup_reputation_hook.mjs
skill.json
SKILL.md
test/
reputation_check.test.mjs
setup_reputation_hook.test.mjs
clawsec-feed/
.clawhubignore
advisories/
feed.json
feed.json.sig
CHANGELOG.md
README.md
skill.json
SKILL.md
clawsec-nanoclaw/
advisories/
feed-signing-public.pem
CHANGELOG.md
docs/
INTEGRITY.md
SKILL_SIGNING.md
guardian/
integrity-monitor.ts
policy.json
host-services/
advisory-cache.ts
integrity-handler.ts
ipc-handlers.ts
skill-signature-handler.ts
INSTALL.md
lib/
advisories.ts
local_file_io.ts
risk.ts
signatures.ts
types.ts
mcp-tools/
advisory-tools.ts
integrity-tools.ts
signature-verification.ts
README.md
skill.json
SKILL.md
test/
security-hardening.test.mjs
clawsec-scanner/
CHANGELOG.md
hooks/
.gitkeep
clawsec-scanner-hook/
handler.ts
HOOK.md
lib/
.gitkeep
report.mjs
types.ts
utils.mjs
README.md
scripts/
.gitkeep
dast_hook_executor.mjs
dast_runner.mjs
query_cve_databases.mjs
runner.sh
sast_analyzer.mjs
scan_dependencies.mjs
setup_scanner_hook.mjs
skill.json
SKILL.md
test/
.gitkeep
cve_integration.test.mjs
dast_harness.test.mjs
dependency_scanner.test.mjs
lib/
test_harness.mjs
reviewer_regressions.test.mjs
sast_engine.test.mjs
clawsec-suite/
.clawhubignore
advisories/
feed-signing-public.pem
feed.json
feed.json.sig
CHANGELOG.md
HEARTBEAT.md
hooks/
clawsec-advisory-guardian/
handler.ts
HOOK.md
lib/
advisory_scope.mjs
feed.mjs
local_file_io.mjs
matching.ts
state.ts
suppression.mjs
types.ts
utils.mjs
version.mjs
README.md
scripts/
discover_skill_catalog.mjs
generate_checksums_json.mjs
guarded_skill_install.mjs
local_file_io.mjs
setup_advisory_cron.mjs
setup_advisory_hook.mjs
sign_detached_ed25519.mjs
verify_detached_ed25519.mjs
skill.json
SKILL.md
test/
advisory_application_scope.test.mjs
advisory_suppression.test.mjs
feed_verification.test.mjs
fuzz_properties.js
fuzz_properties.test.mjs
fuzz_semver_scope_suppression.test.mjs
guarded_install.test.mjs
heartbeat_version_check.test.mjs
lib/
.gitkeep
test_harness.mjs
path_resolution.test.mjs
setup_disclosure.test.mjs
skill_catalog_discovery.test.mjs
clawtributor/
.clawhubignore
CHANGELOG.md
README.md
reporting.md
skill.json
SKILL.md
hermes-attestation-guardian/
CHANGELOG.md
lib/
attestation.mjs
cron.mjs
diff.mjs
feed.mjs
semver.mjs
README.md
scripts/
check_advisories.mjs
generate_attestation.mjs
guarded_skill_verify.mjs
refresh_advisory_feed.mjs
setup_advisory_check_cron.mjs
setup_attestation_cron.mjs
verify_attestation.mjs
skill.json
SKILL.md
test/
attestation_cli.test.mjs
attestation_diff.test.mjs
attestation_schema.test.mjs
feed_verification.test.mjs
guarded_skill_verify.test.mjs
hermes_attestation_sandbox_regression.sh
setup_advisory_check_cron.test.mjs
setup_attestation_cron.test.mjs
hermes-traffic-guardian/
CHANGELOG.md
lib/
.gitkeep
README.md
scripts/
.gitkeep
skill.json
SKILL.md
SPEC.md
test/
.gitkeep
nanoclaw-traffic-guardian/
CHANGELOG.md
host-services/
.gitkeep
lib/
.gitkeep
mcp-tools/
.gitkeep
README.md
skill.json
SKILL.md
SPEC.md
test/
.gitkeep
openclaw-audit-watchdog/
... 245 moreFAQ
clawsec is a Claude Code plugin with 16 hand-picked skills for security work, indexed on Flowy. Install it with the command on its page. It includes claw-release, clawsec-clawhub-checker, clawsec-feed. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is clawsec?
- A complete security skill suite for OpenClaw, Hermes, PicoClaw and NanoClaw agents (and variants). Protect your SOUL.md (etc') with drift detection, live security recommendations, automated audits, and skill integrity verification. All from one installable suite.
- How do I install clawsec?
- Run these in Claude Code: npx -y skills add prompt-security/clawsec --agent claude-code. Then prompt normally.
- Does clawsec auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is clawsec free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.