agentic-actions-auditor

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires fetching full workflow YAML and explicitly instructs the agent to include YAML "evidence" snippets and capture env/token fields (which may contain secret literals), forcing the LLM to read and potentially output secret values verbatim.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The skill’s required runtime workflow is static GitHub Actions security analysis that fetches and reads workflow YAML files from a (user-supplied) target repo via GitHub Contents API/gh and then parses with.prompt/env fields from that YAML; it does not ingest arbitrary outsider-authored free text unless it is contained in those repo workflow files as first-party repo content.