← Back to Scanner

github-mentions Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower
Source:
SHA-256:

github-mentions is an AI agent skill, created by gigi-trifle and published at openclaw/skills. ClawSecure audited github-mentions across 5 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 98/100 (Safe). The 2 findings concentrate in Policy Violation and Verification, including No GitHub source URL - cannot verify agent origin and Skill manifest does not include a 'license' field. Specifying a license.... None were rated high or critical severity.

Is github-mentions safe?

ClawSecure audited github-mentions and assigned a security score of 98/100 (Safe), identifying 2 findings across Policy Violation and Verification. Review the findings below before installing.

What did ClawSecure find in github-mentions?

ClawSecure identified 2 findings in github-mentions, concentrated in Policy Violation and Verification. The most severe include No GitHub source URL - cannot verify agent origin and Skill manifest does not include a 'license' field. Specifying a license....

How was github-mentions audited?

ClawSecure ran github-mentions through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 5 files from openclaw/skills.

What does a score of 98 mean?

ClawSecure assigned github-mentions a security score of 98/100, placing it in the Safe range. Scores of 80 or above qualify for ClawSecure Verified status; the 2 findings detected are lower-severity. ClawSecure derives this score with a weighted deduction model (critical -20, high -10, medium -5, low -2 from a base of 100).

Audit Findings for github-mentions

ClawSecure detected 2 security findings in github-mentions, spanning Policy Violation and Verification.

Each finding is expandable in the interactive list below.

3-Layer Audit Protocol

Security Recommendations for github-mentions

Resolve policy violations
github-mentions trips ClawSecure policy checks. Review each flagged pattern against your security policy and remediate or document an accepted exception before production use.
Pin dependencies to exact versions
Unpinned dependencies allow supply-chain attacks where a compromised version is pulled in automatically. Use exact version numbers in package.json (for example 1.2.3 instead of ^1.2.3) to keep unauthorized code out of your dependency tree. ClawSecure checks every dependency against known CVE databases.
Add a config.json permissions manifest
A config.json file declares what permissions an agent component needs: file system access, network requests, shell execution and more. Without it, users have no visibility into what the component can do before installing. Adding a permissions manifest is the single most impactful security improvement for any AI agent skill.

Related Security Research

OWASP ASI Top 10 Explained: The Complete Guide to AI Agent Security StandardsUnderstanding Our 3-Layer Audit ProtocolBest AI Agent Security Tools in 2026: How to Choose

Related AI Agent Security Audits

TestFilesScore 95/100deep-research-proScore 85/100gogScore 95/100sql-toolkitScore 95/100confluenceScore 95/100

Scanned on February 7, 2026. github-mentions is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.

Start Your Free Scan