pentestcompanion-workspace

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes multiple examples that embed API keys, bearer tokens, webhook URLs, and other secrets directly into curl commands, shell functions, and config files (e.g., PCLOG_TOKEN, Authorization: Bearer pcsk_your_token, SMTP_PASSWORD, RESEND_API_KEY), which would require the LLM to place secret values verbatim into generated commands/code, creating an exfiltration risk.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The installation steps explicitly run "git clone https://github.com/Poellie01/PentestCompanion.git" followed by executing the fetched code (python app.py / docker compose up), so the GitHub URL is a runtime external dependency that results in executing remote code.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The prompt includes explicit instructions that weaken security controls (e.g., telling users to set SSRF_BLOCK_PRIVATE=false to allow private IP access) and encourages running system-altering commands (docker compose up/down, docker exec, flask db upgrade) which collectively push the agent to bypass protections and modify host/container state.