rp-investigate-v2

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The protocol requires agents to read repo files and append exact file:line evidence and code snippets into the investigation report, so if those files contain API keys, tokens, or passwords the LLM would likely need to reproduce them verbatim in its output, creating an exfiltration risk.