ClawAudit verdict

agentify

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Web page analysis and rewriting tool that evaluates HTML/JSX/Svelte code for agent-friendliness across 9 documented categories and generates improvement recommendations; no network calls, no credential access, and no execution sinks — purely a code analysis and transformation assistant.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

60
security
90
transparency
70
maintenance

Findings (2)

Pattern match critical

<script> tag in markdown — potential code injection

references/frameworks.md · code · <script

Pattern match medium

Accesses OpenClaw config/secrets directly

README.ja.md · prose · downgraded · ~/.openclaw/openclaw.json

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API