normalize-id-scan-pdf
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted PDF files (ID scans) which could contain embedded instructions intended to influence the agent's behavior during the review process.
- Ingestion points: The
scripts/fix_id_scan_pdf.pyscript reads user-provided PDF files. - Boundary markers: The skill lacks explicit instructions for the agent to ignore or delimit potentially malicious content found within the processed documents.
- Capability inventory: The agent is instructed to execute Python scripts, manage virtual environments (
pip install), and use system utilities likexdg-open,open, orpowershell.exeto open files. - Sanitization: No sanitization of the PDF text is implemented before the results are presented to the agent.
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the agent to install the
pypdflibrary usingpipwithin a local virtual environment if the dependency is missing. - [COMMAND_EXECUTION]: The workflow relies on executing shell commands to run the processing script and utilizes local system utilities (
xdg-open,open,powershell.exe) or browser commands to display the final PDF output for human verification.
Audit Metadata