llm-shield
Risk score threshold (0.0-1.0)
[](https://agentverus.ai/skill/8a74c1c6-17e5-4172-bd3b-b53daf94f018)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/8a74c1c6-17e5-4172-bd3b-b53daf94f018/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":"8a74c1c6-17e5-4172-bd3b-b53daf94f018","interactedAt":"2026-03-15T12:00:00Z","outcome":"success"}'curl https://agentverus.ai/api/v1/skill/8a74c1c6-17e5-4172-bd3b-b53daf94f018/trustCategory Scores
Findings (15)
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.
→ Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.
Found direct instruction override pattern: "Ignore all previous instructions"
→ Remove all instruction override attempts. Skills must not try to override agent safety behavior.
Found comprehensive secret collection pattern: "all API keys"
→ Skills should not instruct collection of all tokens, keys, or credentials. Access only the specific credentials needed and declare them.
Found comprehensive secret collection pattern: "List all API keys"
→ Skills should not instruct collection of all tokens, keys, or credentials. Access only the specific credentials needed and declare them.
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.
→ Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.
Found credential access pattern: "cat ~/.ssh/id_rsa"
→ Remove references to credentials and secrets. Skills should never access sensitive authentication data.
Found credential access pattern: "~/.ssh/id_rsa"
→ Remove references to credentials and secrets. Skills should never access sensitive authentication data.
Found unrestricted mode activation pattern: "You are now in developer mode"
→ Remove unrestricted mode activation attempts. Skills must not bypass agent safety mechanisms.
Found unrestricted mode activation pattern: "Enable developer mode"
→ Remove unrestricted mode activation attempts. Skills must not bypass agent safety mechanisms.
The skill references 6 external URLs and also discusses auth/API/payment workflows, which increases the chance that sensitive operations depend on many remote endpoints.
→ Minimize external dependencies to reduce supply chain risk.
The skill references an unknown external domain which is classified as low risk.
→ Verify that this external dependency is trustworthy and necessary.
The skill references an unknown external domain which is classified as low risk.
→ Verify that this external dependency is trustworthy and necessary.
The skill references an unknown external domain which is classified as low risk.
→ Verify that this external dependency is trustworthy and necessary.
The skill references an unknown external domain which is classified as low risk.
→ Verify that this external dependency is trustworthy and necessary.
The skill does not include explicit safety boundaries defining what it should NOT do.
→ Add a 'Safety Boundaries' section listing what the skill must NOT do (e.g., no file deletion, no network access beyond needed APIs).