submit
Warn
Audited by Socket on May 10, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the stated purpose is coherent, and the confirmation gate meaningfully limits abuse, but the skill forwards credentials and report contents through opaque MCP tooling with unverifiable data flow. This is not confirmed malicious, yet the hidden submission path and dependency trust gaps create medium risk for credential exposure or unintended routing.
Confidence: 84%Severity: 64%
Audit Metadata