ffuf-web-fuzzing

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to capture and embed user-provided authentication tokens, cookies, and API keys verbatim into raw request files and command examples (and even includes example tokens), requiring the LLM to handle secrets in output — an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs the agent to analyze ffuf outputs derived from arbitrary target web servers (e.g., "ffuf -o results.json" and "ffuf_helper.py analyze results.json" and the "When analyzing ffuf results for users" section/Notes for Claude), which clearly ingests untrusted public web content (responses from target sites) and uses that content to drive follow-up actions and decisions.