pdf-processing
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides capabilities to ingest content from external PDF files which represents a potential indirect prompt injection surface.
- Ingestion points: The script
scripts/extract.pyand snippets inSKILL.mdread data from PDF documents. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are included in the provided code.
- Capability inventory: The skill performs file system reads (PDF files) and writes (output files).
- Sanitization: No sanitization or filtering of extracted PDF content is performed.
Audit Metadata