read-bin-docs
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides tools to extract text from external, potentially untrusted PDF files. This text is then processed by the agent, creating a surface for indirect prompt injection attacks where a malicious document could contain hidden instructions to override agent behavior.
- Ingestion points: The skill ingests data from the pdf_file provided to the extraction script in scripts/extract_pdf_text.py.
- Boundary markers: The skill does not use specific delimiters or instructions to notify the agent that the extracted text is untrusted data.
- Capability inventory: The associated script scripts/extract_pdf_text.py has the ability to read and write files on the local system.
- Sanitization: There is no evidence of text sanitization or verification in scripts/extract_pdf_text.py to prevent malicious payloads.
Audit Metadata