code-reviewer
Warn
Audited by Socket on May 20, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the skill’s purpose is coherent, but it grants an autonomous agent high-leverage review behavior over untrusted repository content and loosely specified external/local tooling. Main concerns are indirect prompt injection and ambiguous tool provenance, not confirmed malware or credential theft.
Confidence: 86%Severity: 64%
Audit Metadata