reconnaissance
Warn
Audited by Socket on May 2, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill is internally consistent, but its stated purpose is to equip an AI agent with offensive reconnaissance and active scanning capabilities against real targets. There are no major credential-harvesting or exfiltration indicators in the text, and installer provenance is mostly acceptable from the provided evidence, but the combination of security-tooling, active network probing, TLS bypass guidance, /etc/hosts modification, and transitive use of /osint makes this a high-risk agent skill.
Confidence: 90%Severity: 87%
Audit Metadata