recon-dir-scan

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt includes explicit examples that embed credentials verbatim into commands and headers (e.g., Authorization: Bearer TOKEN, Cookie: session=YOUR_SESSION_TOKEN, https://user:pass@...), which would encourage or require an agent to accept and output real secret values directly if filled in.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and reference docs explicitly instruct running ffuf/gobuster/feroxbuster against arbitrary target URLs (e.g., "ffuf -w wordlist.txt -u https://target.com/FUZZ") and even show fetching site assets (references/wordlist_guide.md: "curl -s https://target.com/app.js | ..."), and the included parsing scripts (scripts/ffuf_results_parser.py, status_code_analyzer.py) consume and act on those external responses, so untrusted third‑party web content is ingested and can influence subsequent analysis/actions.