pdf-toolkit
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the execution of a local Python script,
scripts/pdf_auditor.py, to perform PDF inspections. This is the primary and intended mechanism for the tool's functionality. - [INDIRECT_PROMPT_INJECTION]: The skill acts as a data ingestion surface by parsing external PDF files to extract metadata strings such as Author, Title, and XMP data.
- Ingestion points: The
scripts/pdf_auditor.pyscript reads the raw byte content of user-provided PDF documents from the local filesystem. - Boundary markers: The script outputs extracted metadata in a plain-text or JSON report format; it does not implement specific delimiters or safety instructions to prevent an agent from interpreting the extracted content as instructions.
- Capability inventory: The script is limited to read-only file access and printing results to standard output. It does not contain network request logic, file-writing capabilities, or subprocess execution triggers based on the parsed metadata.
- Sanitization: The script performs standard PDF string decoding (handling hex and UTF-16BE encodings) but does not sanitize the resulting text content for potential prompt injection keywords.
Audit Metadata