pr-comments-audit
Warn
Audited by Socket on Oct 5, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill's purpose matches PR review workflows, but it explicitly authorizes autonomous external actions—pushing code and posting/resolving PR comments—without approval. No malicious installer or obvious exfiltration path is shown, yet the hidden helper script and lack of data-flow detail keep risk elevated.
Confidence: 84%Severity: 72%
Audit Metadata