receipts
Warn
Audited by Socket on Jul 16, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the stated purpose is plausible, but the skill achieves it by running an external local script at load time via pre-execution syntax. That script lives outside the reviewed skill, has no verifiable provenance in the provided evidence, and runs before normal review, making the skill high-risk despite no confirmed exfiltration or remote download in the visible content.
Confidence: 84%Severity: 78%
Audit Metadata