skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/drawing-analyzer/Gen Agent Trust Hub
drawing-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes construction drawings (PDFs) provided by the user, creating a surface for indirect prompt injection.\n
- Ingestion points: SKILL.md uses the pdfplumber library to extract text from external PDF files.\n
- Boundary markers: Extracted text is not wrapped in delimiters or accompanied by instructions to ignore potential injection attempts within the drawings.\n
- Capability inventory: The skill is designed for file system access (read-only for drawings) and text extraction/analysis.\n
- Sanitization: No sanitization or filtering is applied to the extracted text from the PDF files before it is processed by the agent.
Audit Metadata