skills/wilfriedago/dotfiles/remotion/Gen Agent Trust Hub

remotion

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads screen assets from Google Cloud Storage (storage.googleapis.com) using URLs retrieved from the Stitch API.\n- [EXTERNAL_DOWNLOADS]: Installs standard video processing libraries from the npm registry, specifically @remotion/transitions and @remotion/animated-emoji.\n- [COMMAND_EXECUTION]: Orchestrates video production using the Remotion CLI (npx remotion render) and manages asset downloads via a Bash script (scripts/download-stitch-asset.sh).\n- [PROMPT_INJECTION]: Identifies a surface for indirect prompt injection where untrusted data (titles and descriptions) from Stitch projects is used to generate video overlays.\n
  • Ingestion points: Data enters the context via [stitch_prefix]:get_screen calls in SKILL.md.\n
  • Boundary markers: No explicit instructions are provided to the agent to delimit or ignore instructions within the fetched metadata.\n
  • Capability inventory: The skill has capabilities for file system access (Write), network requests (web_fetch), and shell execution (Bash).\n
  • Sanitization: There are no explicit sanitization or validation steps defined for the external content before it is processed into components.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 09:15 PM