assimilate-popular-wor…
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md…
@a5c-aiInstall SkillAutomation
Skill
/security-hardening
AIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.
Claude Code
$ npx -y skills add a5c-ai/babysitter --skill security-hardening --agent claude-code
Codex
$ npx skills add a5c-ai/babysitter --skill security-hardening -a codex -y
Cursor
$ npx skills add a5c-ai/babysitter --skill security-hardening -a cursor -y
Gemini CLI
$ npx skills add a5c-ai/babysitter --skill security-hardening -a gemini-cli -y
GitHub Copilot
$ npx skills add a5c-ai/babysitter --skill security-hardening -a github-copilot -y
OpenCode
$ npx skills add a5c-ai/babysitter --skill security-hardening -a opencode -y
Windsurf
$ npx skills add a5c-ai/babysitter --skill security-hardening -a windsurf -y
SKILL.md
security-hardening.SKILL.mdname: security-hardening
description: AIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.
allowed-tools: Read, Write, Edit, Bash, Grep, Glob, WebFetch, WebSearch, Agent, AskUserQuestion
graph:
domains: [domain:software-engineering]
skillAreas: [skill-area:agentic-loops, skill-area:orchestration-loop]
workflows: [workflow:feature-development]
topics: [topic:developer-experience]
roles: [role:tech-lead, role:backend-engineer]
- When processing untrusted inputs
- Security audits of agent-generated code
- Compliance verification (OWASP Top 10, CIS)
AIDefence Layers
1. **Prompt Injection Detection** - Pattern + heuristic blocking 2. **Input Validation** - Path traversal, type coercion, parameter sanitization 3. **Static Analysis (SAST)** - Vulnerability scanning, CWE matching 4. **Sandboxed Execution** - Network isolation, filesystem restrictions, resource limits 5. **Output Sanitization** - Secrets, PII, injection vector redaction
Security Levels
| Level | Layers | Use Case | |-------|--------|----------| | standard | SAST + validation + sanitization | Routine audits | | elevated | + threat modeling + compliance | Pre-release audits | | maximum | + sandbox + full STRIDE + remediation | Critical systems |
Agents Used
- `agents/security-auditor/` - Vulnerability detection
- `agents/reviewer/` - Code quality verification
Tool Use
Invoke via babysitter process: `methodologies/ruflo/ruflo-security-audit`
Read more
name: security-hardening description: AIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling. allowed-tools: Read, Write, Edit, Bash, Grep, Glob, WebFetch, WebSearch, Agent, AskUserQuestion graph: domains: [domain:software-engineering] skillAreas: [skill-area:agentic-loops, skill-area:orchestration-loop] workflows: [workflow:feature-development] topics: [topic:developer-experience] roles: [role:tech-lead, role:backend-engineer]
- When processing untrusted inputs
- Security audits of agent-generated code
- Compliance verification (OWASP Top 10, CIS)
AIDefence Layers
1. **Prompt Injection Detection** - Pattern + heuristic blocking 2. **Input Validation** - Path traversal, type coercion, parameter sanitization 3. **Static Analysis (SAST)** - Vulnerability scanning, CWE matching 4. **Sandboxed Execution** - Network isolation, filesystem restrictions, resource limits 5. **Output Sanitization** - Secrets, PII, injection vector redaction
Security Levels
| Level | Layers | Use Case | |-------|--------|----------| | standard | SAST + validation + sanitization | Routine audits | | elevated | + threat modeling + compliance | Pre-release audits | | maximum | + sandbox + full STRIDE + remediation | Critical systems |
Agents Used
- `agents/security-auditor/` - Vulnerability detection
- `agents/reviewer/` - Code quality verification
Tool Use
Invoke via babysitter process: `methodologies/ruflo/ruflo-security-audit`
Ships withbabysitter
Enforce obedience on agentic workforces. Manage extremely complex workflows through deterministic, hallucination-free self-orchestration.
1.9k200 skills3 agents1 MCP
Stars on GitHub
Momentum
- stars in total
- 1.9k
Other skills on babysitter.
@a5c-aiInstall Skillbabysit-babysitter-iss…
This skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process…
@a5c-aiInstall Skillcatalog-babysitter-use…
Discover public GitHub repositories that import defineTask from @a5c-ai/babysitter-sdk and maintain a deduplicated catalog of…
@a5c-aiInstall Skillfix-failing-pipelines
This skill should be used when the user asks to "fix pipelines", "fix CI", "check staging pipelines", "fix failing workflows",…
@a5c-aiInstall Skillprocess-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase…
@a5c-aiInstall Skillretrospect-external-ba…
For a repository in the babysitter-users catalog, locate its babysitter processes and any committed runs (.a5c/runs/<runId>/) and…
@a5c-aiInstall SkillMore skills from other plugins.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…
@browser-useInstall Skillagent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…
@vercel-labs-2Install Skill
Questions about security-hardening.
- Which coding agents can use security-hardening?
- security-hardening installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.