drawing-analyzer

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow in SKILL.md:37-42 ingests extracted outsider-authored drawing text (e.g., text/sheet_NNN.txt, rendered sheet_NNN.png contents) from the user-supplied merged.pdf into the agent’s LLM context as “the query” reads those artifacts and uses them to answer.