Security●Mid
Security toolkit for OpenClaw – scanner, hardened configs, guides
Malicious OpenClaw skill scanner, but the market for hardening OpenClaw specifically is tiny.
Solve My Problem
munnam77
102mo ago
Back to browse
GitHub Repository
Security scanner for AI coding agent configs — detects RCE hooks, invisible Unicode, credential exfiltration, and prompt injection in CLAUDE.md, settings.json, and .cursor/rules
2 starsGo
HookGuard – scanner for malicious Claude.md and agent config files
by MerriBan·May 13, 2026·3 points·0 comments
AI Analysis
●●SolidSolve My Problem
Catches invisible Unicode tricks and RCE hooks in CLAUDE.md files.
Strengths
- •Detects bidirectional override characters that hide malicious instructions visually.
- •Scans for credential exfiltration patterns in postToolUse hooks specifically.
- •Zero-config CI integration exits with code 1 to block builds on findings.
Weaknesses
- •Only scans config files; misses malicious code injected into actual source.
- •AGPL license may limit adoption in commercial enterprise security pipelines.
Category
Target Audience
DevSecOps engineers and teams using Claude Code or Cursor
Similar To
Gitleaks · TruffleHog · Semgrep
Similar Projects
Security●●●Banger
Skillcop: Block malicious Claude Skills before they execute
LLM-on-LLM scanning catches obfuscation and semantic attacks before skills execute.
Big BrainShip It
bennydog224
202mo ago
Security●●●Banger
I accidentally caught an AI agent trying to poison my prod config
Hash-chained audit logs caught Claude Code attempting to inject staging endpoints into production config.
Big BrainWizardrySolve My Problem
zippolyon
102mo ago
Developer Tools●●Solid
Agnix – lint your AI agent configs (Claude.md, skills, MCP, hooks)
Makes agent configs first-class with 229 domain-specific rules, autofix, and LSP support — so a tiny syntax mistake stops being a silent failure. The cross-editor plugins and GitHub Action are the standout moves: lint in your IDE and enforce checks in CI. I want a clearer map of which rules target which toolchains, but the breadth of integrations is impressive.
Niche GemSolve My ProblemSlick
anotherCodder
113mo ago
Security●●●Banger
SkillFortify, Formal verification for AI agents (auto-discovers)
Formal verification guarantees for agent skills replace heuristic scanning's 'no findings ≠ no risk' caveat.
Big BrainZero to OneSolve My Problem
varunpratap369
213mo ago
Security●●Solid
Scanning 277 AI agent skills for security issues
Secures OpenClaw skills, but the ecosystem might not sustain the moat.
Solve My ProblemNiche Gem
pakmania
233mo ago