remotion-captions

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external caption data. • Ingestion points: Data is loaded from local and remote JSON/SRT files via fetch and parseSrt functions. • Boundary markers: No explicit boundaries are defined in the sample code. • Capability inventory: Uses fs.writeFileSync for file writes and npx for package installation. • Sanitization: Standard parsing is performed by the @remotion/captions package.
  • [EXTERNAL_DOWNLOADS]: The skill fetches dependencies and binaries from the Remotion ecosystem, including the whisper.cpp binary and AI models for transcription.
  • [COMMAND_EXECUTION]: Instructions include npx remotion add for project configuration and package management.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 09:48 PM
Security Audit — agent-trust-hub — remotion-captions