skills/getedgehq/skills/skill-battle/Gen Agent Trust Hub

skill-battle

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The script scripts/render_card.py utilizes __import__('os') to dynamically load the os module and access environment variables. Furthermore, the test suite in tests/test_render_card.py uses importlib.util and exec_module to load the script into the test environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as an ingestion surface for evaluation data which is processed and rendered into visual artifacts.
  • Ingestion points: The scripts/render_card.py script reads JSON-formatted experiment data from paths provided via command-line arguments.
  • Boundary markers: Not applicable for this data processing workflow.
  • Capability inventory: The script has the capability to create directories and write SVG and PNG files to the local file system.
  • Sanitization: The rendering logic uses html.escape to sanitize all text fields extracted from the input JSON before they are embedded in the SVG output, providing protection against injection in the generated files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 08:43 PM