pentagi

Warn

Audited by Socket on Oct 27, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS: the skill is internally consistent with its stated purpose as an autonomous pentesting platform and uses same-org official sources, so it does not show credential harvesting or deceptive exfiltration. However, the purpose itself is high risk: it enables AI-driven offensive security actions, processes untrusted external content, mounts Docker control surfaces, and can send target details to third-party LLM/search providers.

Confidence: 91%Severity: 83%
Audit Metadata
Analyzed At
Oct 27, 2026, 03:35 AM
Package URL
pkg:socket/skills-sh/terminalskills%2Fskills%2Fpentagi%2F@afce9ddd3f86f43d0e12fe13255fc1d8b18ff26019e5cf318b361b38a3cc689d