code-execution
Warn
Audited by Socket on Sep 17, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the skill's capabilities broadly match its purpose, but the trust model is weak because it asks the agent/user to run a marketplace-provided shell installer for a local execution runtime. The main risks are supply-chain trust in `setup.sh` and high-impact local/git actions, especially `git_push`; there is limited evidence of overt credential theft or covert exfiltration in the provided text.
Confidence: 82%Severity: 62%
Audit Metadata