agentic-actions-auditor

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly instructs the agent to capture token fields and to include YAML code snippets/evidence in reports (which would include any literal API keys or secrets present in the workflow), thereby requiring 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 (high risk: 0.75). Yes: in remote analysis mode the skill fetches outsider-authored workflow YAML from a user-supplied GitHub repo via gh api .../contents/... and then reads fields like with.prompt/with.system-prompt into the agent’s analysis/report context (free text originating from that remote repo).