affinage
Warn
Audited by Socket on Oct 19, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The GitHub-focused data flows and capabilities mostly fit the stated PR-triage purpose, and network calls stay within official GitHub surfaces. However, the skill relies on an unverifiable local `affinage.pyz` bundle to fetch PR data and post replies, and it can automate reply posting/publication in `--auto` mode; that makes the execution trust materially risky even without clear malicious intent.
Confidence: 89%Severity: 72%
Audit Metadata