render-logo-equation-card

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The script _fonts.py downloads Roboto font files from the official Google Fonts repository on GitHub if compatible system fonts are not detected. This is a functional requirement for rendering text and targets a trusted source.
  • [COMMAND_EXECUTION]: The skill uses the subprocess module in compose.py and measure_motion.py to execute ffmpeg and ffprobe. These calls are used for video encoding, compositing, and motion analysis, which are the primary functions of the skill. The commands are constructed using list-based arguments, which follows security best practices to prevent shell injection.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-controlled content from card.json (such as headlines and CTA text). To mitigate risks associated with untrusted input, render_card.py implements strict guardrails, including banned word lists, character restrictions (disallowing dashes), and layout validation before any rendering occurs.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 01:55 PM