pdf-processing
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill extracts content from external PDF documents, creating a surface for indirect prompt injection where malicious instructions embedded in a file could influence the agent's behavior.
- Ingestion points: PDF text and table extraction routines described in SKILL.md.
- Boundary markers: No delimiters or specific instructions for the agent to ignore content within the extracted text are provided.
- Capability inventory: The skill utilizes pdfplumber and PyPDF2 for data extraction and document manipulation; no high-risk system commands or network operations are present in the provided file.
- Sanitization: The documentation lacks instructions for sanitizing or validating the extracted content before it is processed by the AI.
Audit Metadata