pdf-extractor
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted PDF files and outputs the extracted text to the agent, creating a surface for indirect prompt injection attacks.\n
- Ingestion points: The
scripts/pdf-extract.jsfile reads document content usingfs.readFileSyncbased on the--fileargument.\n - Boundary markers: The script outputs raw extracted text directly to stdout without using delimiters or protective headers to signal the boundary between data and instructions.\n
- Capability inventory: The script is limited to file system read access and basic regex parsing; it lacks subprocess execution, network access, or dynamic code evaluation capabilities.\n
- Sanitization: The tool implements basic character filtering (
match[1].replace(/[^\x20-\x7E\n\r\t]/g, '')) to remove non-readable bytes, but it does not perform any semantic analysis or instruction filtering on the content.
Audit Metadata