security-scan
Warn
Audited by Socket on Mar 30, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
Mostly coherent security-audit skill with proportionate local file access, but it depends on an external CLI and has mild provenance ambiguity between ECC, the npm package, and the linked GitHub repo/action. Optional Opus mode forwards scan context using ANTHROPIC_API_KEY, which is disclosed and aligned with purpose but increases risk. Overall this is better classified as suspicious/medium-risk than benign due to supply-chain trust and external-analysis exposure, not because of clear malicious behavior.
Confidence: 79%Severity: 56%
Audit Metadata