Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands to interact with system utilities like
pdftotext,pandoc, andwkhtmltopdffor document conversion and text extraction. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external PDF files, which could contain adversarial instructions meant to influence the agent's behavior.
- Ingestion points: Reading PDF files through
fitz(PyMuPDF) andpdftotextutilities (SKILL.md). - Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions found within the processed documents.
- Capability inventory: The skill utilizes shell execution for document tools and Python file operations for merging/splitting (SKILL.md).
- Sanitization: No sanitization, escaping, or validation mechanisms are described for the content extracted from PDFs.
- [EXTERNAL_DOWNLOADS]: The documentation suggests installing standard, widely-recognized Python packages such as
pymupdf,reportlab, andpdfkit, as well as system utilities likepoppler-utils.
Audit Metadata