service-boundary-analysis

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill requires capturing code/config "evidence" and excerpts (file, line/range, symbol, evidence) with no guidance to redact secrets, so if repository configs or code contain API keys/passwords the LLM would be expected to include them verbatim in its output, creating an exfiltration risk.