skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/specification-extractor/Gen Agent Trust Hub
specification-extractor
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes external PDF files, which introduces a surface for indirect prompt injection where instructions embedded in documents might influence agent behavior. \n
- Ingestion points: The
extract_from_pdfmethod inSKILL.mdreads text directly from user-provided PDF files. \n - Boundary markers: Extracted text is aggregated into strings without specific delimiters or instructions to the agent to ignore any embedded commands within the parsed content. \n
- Capability inventory: The skill requests and uses filesystem read permissions (via
pdfplumber) to access documents. \n - Sanitization: No sanitization or filtering is performed on the extracted text before it is used. \n- [EXTERNAL_DOWNLOADS]: The skill specifies a dependency on the well-known
pdfplumberPython package for PDF parsing functionality.
Audit Metadata