drawing-quantity-extract
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external PDF drawing files and OCR text results. \n- Ingestion points: Supplied drawing files, physical page lists, and text/coordinate extraction data (SKILL.md, Step 2). \n- Boundary markers: The instructions do not define specific boundary markers or delimiters to separate drawing content from agent instructions, nor do they include warnings to ignore embedded text commands. \n- Capability inventory: The skill allows the use of Bash, Write, and Read tools, providing a surface for command execution or file modification (SKILL.md frontmatter). \n- Sanitization: While the skill classifies text into categories like 'instance' or 'note', it does not explicitly perform sanitization or validation of the extracted strings to prevent them from being interpreted as instructions by the agent (SKILL.md, Step 3).
Audit Metadata