software-engineering-workflow-skill

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

• Third-party content exposure detected (high risk: 0.90). The skill's Investigation stage (stages/01-investigation/investigation-guide.md and the SKILL.md "Investigation" section) explicitly requires reading public APIs/specs/issues, inspecting or cloning upstream/vendor/sample repositories, and recording web links/open-source references—untrusted public third-party content that the agent must interpret and use to drive workflow decisions and next actions.