Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from external PDF files, creating a vulnerability to indirect prompt injection.\n
- Ingestion points: Untrusted content is read using
pypdf,pdfplumber, andpypdfium2as described inSKILL.md, and through the analysis of images converted from PDFs informs.md.\n - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are provided to the agent.\n
- Capability inventory: The skill can write files, execute the included Python scripts, and run system CLI tools like
qpdfandpdftotext.\n - Sanitization: The skill lacks sanitization of extracted text before it is provided to the agent's context.\n- [COMMAND_EXECUTION]: The instructions in
SKILL.md,forms.md, andreference.mdguide the agent to use various command-line utilities, includingpdftotext,qpdf,pdftk,pdftoppm,pdfimages, and ImageMagick'smagickcommand.
Audit Metadata