openedit-to-invideo
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes OpenEdit plans as its primary input. If these plans originate from untrusted external sources, they may contain embedded instructions that could attempt to manipulate the agent's behavior during the rendering, editing, or export phases.
- Ingestion points: OpenEdit plans rendered into MP4 files.
- Boundary markers: None; the instructions do not define delimiters or provide warnings to ignore embedded content within the plans.
- Capability inventory: Rendering plans to MP4, uploading media to
/invideo-media, and performing video edits including cuts, captions, music, and voice generation. - Sanitization: None; the skill does not specify any validation or filtering of the input plan data before processing.
Audit Metadata