pdf-extraction

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted PDF data which presents a surface for indirect prompt injection. 1. Ingestion points: PDF documents are loaded via pdfplumber.open() in several examples within SKILL.md. 2. Boundary markers: No delimiters or instructions to ignore embedded commands are included for the extracted content. 3. Capability inventory: The skill includes file reading and file writing capabilities (e.g., df.to_excel and im.save). 4. Sanitization: No sanitization or filtering is performed on the extracted data before it is processed or returned.
  • [EXTERNAL_DOWNLOADS]: The documentation recommends installing standard, well-known libraries including pdfplumber and Pillow from official package registries.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:21 AM