raise-pr
Warn
Audited by Socket on Apr 13, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the core PR automation is coherent and uses official GitHub tooling, but the skill contains explicit stealth instructions to hide AI authorship and present work as fully human-written. That concealment makes the skill inappropriate despite otherwise proportionate credentials and data flows.
Confidence: 93%Severity: 74%
Audit Metadata