run-debugger

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). This skill requires the model to quote verbatim lines from the Run transcript and AOP as evidence (and to ingest pasted transcripts/AOP), so if those artifacts contain API keys, tokens, cookies, or passwords the LLM would be forced to output them verbatim, creating an exfiltration risk.