iam-policy-reviewer
Warn
Audited by Socket on May 4, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the skill is not overtly malicious and shows no credential exfiltration, external routing, or installer abuse, but its actual footprint is poorly aligned with its thin IAM-review purpose. The combination of auto-activation, unrestricted Bash(cmd:*), and broad security-category scope is disproportionate for a generic guidance skill.
Confidence: 86%Severity: 57%
Audit Metadata