pdf-to-docx
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external PDF data which constitutes an untrusted input source. 1. Ingestion points: Content is read from PDF files using the pdf2docx.Converter and pytesseract as described in SKILL.md. 2. Boundary markers: The instructions lack explicit boundary markers or directives to the agent to ignore any natural language instructions found within the converted text. 3. Capability inventory: The skill utilizes code_execution to run Python scripts and file_operations to read and write documents, providing a functional path for any injected instructions to influence system state. 4. Sanitization: There is no evidence of text sanitization or filtering applied to the extracted content before it is processed by the agent.
Audit Metadata