Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes instructions for the agent to use command-line utilities such as
qpdf,pdftotext, andpdftkfor processing PDF documents. - [DATA_EXPOSURE]: The scripts perform legitimate file system operations, including reading PDF content and writing output files (PDFs, images, and JSON metadata) necessary for document manipulation.
- [PROMPT_INJECTION]: As the skill ingests and processes user-provided PDF documents, it possesses an inherent surface for indirect prompt injection where malicious instructions could be embedded in PDF text; however, no specific exploitable patterns were found in the skill's logic.
- [SAFE]: The
scripts/fill_fillable_fields.pyfile contains a Python monkeypatch to correct a specific data-handling bug in thepypdflibrary, which is a common technical workaround and does not introduce security risks.
Audit Metadata