ffuf-web-fuzzing

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs creating raw request files and examples that include Authorization headers, cookies, and JWTs and tells the agent to insert users' auth tokens/cookies into req.txt for authenticated fuzzing, which requires outputting secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs Claude to analyze ffuf output (e.g., "When analyzing ffuf results for users" and the helper usage "python3 ffuf_helper.py analyze results.json"), which are derived from arbitrary public target websites and public wordlists (e.g., SecLists/GitHub), so the agent is expected to read and act on untrusted, third‑party web content that can influence follow-up actions.