Skip to content
โ† Registry
Trust Report

Skill Audit ๐Ÿ”

ๆ‰ซๆ OpenClaw skills ไธญ็š„ๅฎ‰ๅ…จ้ฃŽ้™ฉ๏ผŒ้˜ฒๆญขไพ›ๅบ”้“พๆ”ปๅ‡ปใ€‚ ---

76
REJECTED
Format: genericScanner: v0.8.0Duration: 6msScanned: 8d ago ยท May 31, 2:06 AMSource โ†’
Embed this badge
AgentVerus REJECTED 76AgentVerus REJECTED 76AgentVerus REJECTED 76
[![AgentVerus](https://agentverus.ai/api/v1/skill/75fc6b22-bb59-462a-b5a1-bbc876162d79/badge)](https://agentverus.ai/skill/75fc6b22-bb59-462a-b5a1-bbc876162d79)
Community Discussion

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.

0 comments

Sign in to comment on this skill

No comments yet. Be the first to share your thoughts.

Continue the workflow

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/trust
Personalized next commands

Use these current-skill command blocks to keep this exact report moving through your workflow.

Record an interaction
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"}'
Fetch trust JSON
curl https://agentverus.ai/api/v1/skill/75fc6b22-bb59-462a-b5a1-bbc876162d79/trust

Category Scores

82
Permissions
100
Injection
90
Dependencies
70
Behavioral
70
Content
75
Code Safety

Findings (8)

criticalDynamic code execution (eval / new Function)-25

eval() or new Function() detected. These execute arbitrary strings as code at runtime, enabling injection attacks and obfuscated payload delivery.

โ”‚ utils.ts โ”‚ WARNING โ”‚ Uses eval() โ”‚

โ†’ Review the code block starting at line 55. Ensure this pattern is necessary and does not pose a security risk.

code-safetyASST-10
highCapability contract mismatch: inferred command execution is not declared-12

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.

Content pattern: eval(

โ†’ Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-03
highPotential data exfiltration: skill reads credentials and sends them to external endpoints-25

The skill contains patterns that actively read credential files and send data to external endpoints, suggesting a possible data exfiltration flow.

Active credential reading and suspicious network exfiltration patterns both present

โ†’ Separate credential access from network operations. If both are needed, declare them explicitly and justify.

behavioralASST-06
mediumCapability contract mismatch: inferred network access is not declared-6

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.

Content pattern: https://owasp.org/www-project-top-10-for-large-language-model-applications/

โ†’ Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-04
mediumSkill path discovery detected (inside code block)-5

Found skill path discovery pattern: "{baseDir}"

node {baseDir}/src/audit.js scan ~/.openclaw/workspace/skills/moltdash

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.

behavioralASST-03
lowUnknown external reference-5

The skill references an unknown external domain which is classified as low risk.

https://owasp.org/www-project-top-10-for-large-language-model-applications/

โ†’ Verify that this external dependency is trustworthy and necessary.

dependenciesASST-04
lowUnknown external reference-5

The skill references an unknown external domain which is classified as low risk.

https://www.moltbook.com/post/cbd6474f-8478-4894-95f1-7b104a73bcd5

โ†’ Verify that this external dependency is trustworthy and necessary.

dependenciesASST-04
lowNo explicit safety boundaries-10

The skill does not include explicit safety boundaries defining what it should NOT do.

No safety boundary patterns found

โ†’ Add a 'Safety Boundaries' section listing what the skill must NOT do (e.g., no file deletion, no network access beyond needed APIs).

contentASST-09