doc-to-txt
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill extracts text from untrusted external document files (.doc, .docx, .pdf). This content is processed without sanitization, creating a surface for indirect prompt injection where malicious instructions embedded in the documents could influence the behavior of an agent reading the output.
- Ingestion points:
scripts/convert.pyreads user-provided document files as input. - Boundary markers: Absent. The skill writes the extracted text directly to an output file without wrapping it in delimiters or providing warnings to downstream consumers about the untrusted nature of the content.
- Capability inventory: The skill has file system write access to save the converted text files.
- Sanitization: Absent. No filtering, escaping, or validation of the extracted text is performed before it is written to the output path.
Audit Metadata