render-airdrop-carousel

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes subprocess.run to orchestrate its rendering pipeline. Specifically, scripts/one_shot.py invokes internal Python scripts (build_card.py and compose_carousel.py), and scripts/compose_carousel.py calls ffmpeg for video encoding and audio multiplexing. All subprocess calls use list-based arguments rather than shell strings, preventing shell injection vulnerabilities.
  • [EXTERNAL_DOWNLOADS]: The skill documentation and one_shot.py facilitate the use of Playwright for capturing high-fidelity screenshots of HTML templates. This involves downloading the Chromium browser binary via playwright install chromium. This is a standard dependency for the tool's stated purpose and originates from a well-known, trusted project (Microsoft Playwright).
  • [DATA_EXFILTRATION]: No unauthorized network operations or exfiltration patterns were detected. Network activity is restricted to the legitimate download of browser binaries during setup and local file operations for asset processing.
  • [PROMPT_INJECTION]: The skill contains instructional content for the agent regarding video durations and asset types but does not include any patterns typical of prompt injection or instructions to bypass safety guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 09:42 AM
Security Audit — agent-trust-hub — render-airdrop-carousel