safe-rm
Warn
Audited by Socket on Oct 6, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the deletion capability matches the stated purpose, but the skill's core executable ai-safe-rm is undocumented and not verifiably sourced. There is no evidence of credential theft or off-host data flow, yet the combination of destructive filesystem access, prompt bypass intent, and an unverifiable local helper makes the overall security risk high.
Confidence: 87%Severity: 72%
Audit Metadata