Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a set of utility scripts and instructions for PDF manipulation using well-known libraries such as
pypdf,pdfplumber, andreportlab. All scripts perform legitimate document processing tasks as described in the documentation. - [DYNAMIC_EXECUTION]: The script
scripts/fill_fillable_fields.pycontains a monkeypatch for thepypdflibrary to resolve a specific formatting issue with selection lists. This involves runtime modification of the library's method, which is documented and used for a benign purpose related to the skill's primary function. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates processing external PDF files, creating a potential surface for indirect prompt injection. The risk is mitigated by the structured workflow involving intermediate data formats (JSON) and the agent's inherent safety guardrails, which apply to the extracted content.
Audit Metadata