re-verify-logic
Warn
Audited by Socket on Oct 11, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill’s stated purpose and local file/data flows are coherent and mostly benign, with no credential harvesting or exfiltration path. The main concern is that it requires external mcp__serena__ tooling with unverifiable provenance from the skill alone, plus unnecessary Bash access for a documentation verifier.
Confidence: 86%Severity: 72%
Audit Metadata