video-shorts
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a local bash script
scripts/verify.shused to lint markdown files produced by the agent. The script is restricted to text parsing using standard tools (grep, awk, sed) and does not perform any network operations, file modifications, or administrative actions. - [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided topics or video transcripts to generate scripts. While this is an ingestion surface, the skill's instructions focus on content structure (hooks, beat sheets), and the provided verification tool is read-only, limiting the impact of potential injection in source data.
- [EXTERNAL_DOWNLOADS]: The skill references several well-known industry sources and video editing tools (e.g., CapCut, OpusClip, Sprout Social) for data and specifications. These are informational references and do not involve downloading or executing untrusted code.
Audit Metadata