Skill Audit ๐
ๆซๆ OpenClaw skills ไธญ็ๅฎๅ จ้ฃ้ฉ๏ผ้ฒๆญขไพๅบ้พๆปๅปใ ---
[](https://agentverus.ai/skill/75fc6b22-bb59-462a-b5a1-bbc876162d79)Community Comments
Public comments are the active feedback surface on skill reports right now. Use them to share implementation notes, edge cases, and operator context.
Sign in to comment on this skill
No comments yet. Be the first to share your thoughts.
Keep this report moving through the activation path: rescan from the submit flow, capture real-world interactions, and wire the trust endpoint into your automation.
https://agentverus.ai/api/v1/skill/75fc6b22-bb59-462a-b5a1-bbc876162d79/trustUse your saved key to act on this report immediately instead of returning to onboarding.
Use these current-skill command blocks to keep this exact report moving through your workflow.
curl -X POST https://agentverus.ai/api/v1/interactions \
-H "Authorization: Bearer at_your_api_key" \
-H "Content-Type: application/json" \
-d '{"agentPlatform":"openclaw","skillId":"75fc6b22-bb59-462a-b5a1-bbc876162d79","interactedAt":"2026-03-15T12:00:00Z","outcome":"success"}'curl https://agentverus.ai/api/v1/skill/75fc6b22-bb59-462a-b5a1-bbc876162d79/trustCategory Scores
Findings (8)
eval() or new Function() detected. These execute arbitrary strings as code at runtime, enabling injection attacks and obfuscated payload delivery.
โ Review the code block starting at line 55. Ensure this pattern is necessary and does not pose a security risk.
The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.
โ Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.
The skill contains patterns that actively read credential files and send data to external endpoints, suggesting a possible data exfiltration flow.
โ Separate credential access from network operations. If both are needed, declare them explicitly and justify.
The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.
โ Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.
Found skill path discovery pattern: "{baseDir}"
โ Treat dynamic skill path resolution and installation-path discovery as local filesystem reconnaissance. Scope which paths may be read or executed from, and avoid broad path probing unless the user explicitly requested it.
The skill references an unknown external domain which is classified as low risk.
โ Verify that this external dependency is trustworthy and necessary.
The skill references an unknown external domain which is classified as low risk.
โ Verify that this external dependency is trustworthy and necessary.
The skill does not include explicit safety boundaries defining what it should NOT do.
โ Add a 'Safety Boundaries' section listing what the skill must NOT do (e.g., no file deletion, no network access beyond needed APIs).