pdf-processing
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements legitimate PDF processing functionality using standard Python libraries such as pdfplumber, pypdf, and pdfrw. The provided scripts are mock implementations intended for demonstration and do not perform any dangerous operations.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external PDF documents, which serves as a potential surface for indirect prompt injection attacks if the documents contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: Text and table extraction operations described in SKILL.md and implemented in scripts/extract_text.py.
- Boundary markers: No explicit boundary markers or instructions to ignore embedded commands were found in the skill instructions.
- Capability inventory: File writing operations are present in FORMS.md for saving filled PDF documents using the pypdf library.
- Sanitization: The skill does not include explicit sanitization or filtering of the content extracted from PDF files.
Audit Metadata