what-we-forgot
Warn
Audited by Socket on May 14, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the skill is internally coherent as a memory/review aid, but its actual behavior presses the agent to inspect broader instructions and autonomously resume work, creating prompt-boundary and action-authorization risk. No credential, install, or external data-flow concerns were found.
Confidence: 91%Severity: 64%
Audit Metadata