skills/daxaur/openpaw/c-video-edit/Gen Agent Trust Hub

c-video-edit

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx to fetch and run the create-video and remotion packages directly from the NPM registry, which is a well-known and trusted service.
  • [COMMAND_EXECUTION]: The skill invokes several command-line tools including npx and editly to manage project setup and video rendering processes.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection.
  • Ingestion points: Data enters the system via the spec.json5 configuration file and the --props CLI argument.
  • Boundary markers: No specific delimiters or safety instructions are defined to separate user data from command logic.
  • Capability inventory: The skill executes subprocesses (npx remotion render, editly) which process the provided data to generate media files.
  • Sanitization: The skill does not implement explicit sanitization or validation for the incoming data structures.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:44 AM
Security Audit — agent-trust-hub — c-video-edit