resolve-pr-feedback
Warn
Audited by Socket on Apr 17, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: The skill is broadly aligned with its stated PR-feedback purpose and uses official GitHub flows, but it grants high-impact autonomous write actions (commit/push/comment/resolve) and processes untrusted PR text while spawning downstream agents. The main concern is operational risk and transitive agent trust, not malware or credential theft.
Confidence: 87%Severity: 62%
Audit Metadata