publish
Warn
Audited by Socket on Sep 15, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The workflow is purpose-aligned for release management and mostly uses official GitHub/npm surfaces, but it grants the agent authority to perform public release and announcement actions end-to-end without additional approval. Risk is further elevated because the skill depends on an unverified external/local messaging CLI (agent-discordbot) that handles bot-authenticated posting; that credential-forwarding path is not provenance-validated in the skill.
Confidence: 77%Severity: 82%
Audit Metadata