NYC

venue-templates

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • COMMAND_EXECUTION (LOW): The script validate_format.py executes external system utilities (pdfinfo, pdffonts) via subprocess.run. While it correctly uses argument lists to prevent shell injection, it lacks validation for the input file path, which could lead to argument injection if the filename starts with a dash.
  • PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection as it processes external templates and PDF files. Evidence Chain: 1. Ingestion points: customize_template.py (reads templates) and validate_format.py (reads PDFs). 2. Boundary markers: Absent. 3. Capability inventory: File writing and subprocess execution. 4. Sanitization: Absent.
  • DATA_EXPOSURE (LOW): Potential path traversal in customize_template.py and validate_format.py. These scripts accept output filenames and report paths without sanitization, allowing for the possibility of overwriting local files if malicious paths are provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:23 PM