zero
Warn
Audited by Socket on Jun 14, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the stated purpose is plausible, but the skill expands scope by instructing the agent to install a separate skill and grant it wildcard permissions. The external CLI dependency is not inherently malicious, yet the transitive install plus `--skill '*'` makes the trust model broader than necessary for roadmap generation.
Confidence: 100%Severity: 60%
Audit Metadata