multi-agentic-threat-m…
Comprehensive threat modeling for multi-agent systems using CSA MAESTRO 7-layer framework and OWASP Multi-Agentic System Threat…
Security-focused review of native Android and iOS mobile app source code against OWASP MASVS v2.1.0. Use when reviewing mobile codebases, mobile PR diffs, or auditing a mobile module.
$ npx -y skills add owasp/secure-agent-playbook --skill mobile-code-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/mobile-code-reviewContext preview
The summary Claude sees to decide when to auto-load this skill.
Security-focused review of native Android and iOS mobile app source code against OWASP MASVS v2.1.0. Use when reviewing mobile codebases, mobile PR diffs, or auditing a mobile module.
name: mobile-code-review description: Security-focused review of native Android and iOS mobile app source code against OWASP MASVS v2.1.0. Use when reviewing mobile codebases, mobile PR diffs, or auditing a mobile module. license: CC-BY-4.0
Review native Android and iOS source code for security vulnerabilities by following the full procedure in `plays/mobile-code-review.md`.
1. **Scope & Context** — Language (Java/Kotlin/Swift/Obj-C/Dart), platform, app type, sensitive data, exposure. 2. **Platform Detection** — Fingerprint Android (AndroidManifest.xml, build.gradle) and/or iOS (Info.plist, *.xcodeproj). If only a cross-platform shell is detected, declare partial coverage. 3. **Systematic Review by MASVS Group** — For each of the 8 MASVS groups (STORAGE, CRYPTO, AUTH, NETWORK, PLATFORM, CODE, RESILIENCE, PRIVACY) in priority order:
4. **Diff-Specific Analysis** (for PRs) — Focus on changed lines; verify pinning, permissions, and KeyStore/Keychain usage are not weakened. 5. **Produce Findings** — Use `templates/finding.md`. Sort by severity (CRITICAL > HIGH > MEDIUM > LOW > INFO). Deduplicate cross-group findings (cite the most specific MASVS control in `OWASP Ref`).
Scope summary (platform, languages), upstream-pointer note for MASTG IDs (`https://github.com/OWASP/mastg`, `https://mas.owasp.org/MASTG/`), findings sorted by severity using `templates/finding.md` (each finding carries an optional `MASTG references:` bullet listing any non-TEST `@MASTG-<KIND>-####` cross-refs cited in the informing tests, grouped by KIND alphabetically, IDs sorted numerically, omitted when empty), positive observations, severity count table, RESILIENCE static-only notice block, PRIVACY runtime-required caveat for findings against PRIVACY-2/PRIVACY-3, dynamic-test follow-up list (collected from `data/mastg/` entries with `type: [dynamic]` that informed findings).
An open-source security playbook for AI agents. Structured, OWASP-grounded procedures that enable agents to perform security engineering tasks — from code review to AI agent security audits.
Comprehensive threat modeling for multi-agent systems using CSA MAESTRO 7-layer framework and OWASP Multi-Agentic System Threat…
Audit AI agent configurations for security risks — excessive permissions, prompt injection surfaces, data exfiltration paths, and…
Assess agentic AI applications against the OWASP Top 10 for Agentic Applications 2026. Use when reviewing autonomous AI agents,…
Comprehensive AI security verification using OWASP AI Security Verification Standard (AISVS) framework. Use when verifying an…
Comprehensive LLM security assessment against OWASP Top 10 for LLM Applications 2025. Use when reviewing LLM-integrated…
Security review of MCP (Model Context Protocol) server implementations and configurations. Use when auditing MCP server source…