pentest-agent-os

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.85). The skill explicitly instructs the agent to take "凭据" (credentials) and immediately use/expand them and upsert them into the project blackboard, which implies the LLM must handle and emit secret values verbatim into actions/records (exfiltration risk).

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document is an explicit offensive "pentest" skill index that organizes and instructs modules for initial access (phishing), credential/secret hunting, post‑exploitation, lateral movement, OPSEC, zero‑day discovery and proxy/tool bootstrap — indicating intentional malicious/abusive capabilities and operational guidance for intrusions.