structural-analysis

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

• Third-party content exposure detected (high risk: 0.70). The skill’s workflow is explicitly for analyzing a provided source document and producing structured findings from its readable text; if that source is outsider-authored (e.g., a web page, issue/PR text, or uploaded document not authored by the operating user), that free-form prose would be ingested into the agent’s LLM context during runtime analysis.