agentic-actions-auditor

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly instructs fetching workflow YAML and including verbatim evidence snippets and captured fields (e.g., env values, token, prompt/prompt-file contents), which can contain hard-coded secrets or secret values and thus requires the LLM to handle/output secrets verbatim.