restler
Warn
Audited by Socket on Sep 5, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill is internally consistent and uses official Microsoft sources, but its purpose is to arm the agent with an active API fuzzing/security-testing capability that can probe and destabilize external services. This is not malware or credential theft, but it is a high-risk offensive testing skill for an AI agent.
Confidence: 91%Severity: 72%
Audit Metadata