speak-with-dead

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill requires extracting and citing specific artifact contents (files, commit lines, config keys, state files, packet captures) as evidence and deliverables without instructing redaction, which can force the LLM to reproduce secrets found verbatim (API keys, passwords, tokens) in its output.