prompt-engineering
Warn
Audited by Socket on Apr 9, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill’s main behavior is consistent with a prompt-engineering guide, but it relies on a remote-installed vendor CLI, forwards prompts/auth through that CLI, grants broad `infsh *` execution, and suggests installing additional skills. Same-org installer evidence lowers concern from malicious to medium-risk supply-chain and scope issues.
Confidence: 84%Severity: 58%
Audit Metadata