gram
Warn
Audited by Socket on Apr 10, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill is internally consistent as a kill-switch, but its footprint is intentionally high-risk and disproportionate for routine agent management. Same-org tooling lowers malware concern, yet the combination of process killing, network teardown, archive-and-delete behavior, and optional root-wide cleanup makes this a high-risk destructive skill that should only be used with explicit user approval.
Confidence: 90%Severity: 84%
Audit Metadata