cmd-fix-internal-requests
Warn
Audited by Socket on Apr 27, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill’s GitHub automation purpose matches its capabilities, and install trust is largely benign, but it gives an agent high-impact autonomous repo write/public-posting powers while processing untrusted issue content and repo instructions. Main risk is prompt injection and unintended code changes or PRs, not malware or credential theft.
Confidence: 88%Severity: 74%
Audit Metadata