vlog-editor
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external video metadata, clip names, and timeline information which could potentially contain embedded instructions designed to influence the agent's editing decisions.
- Ingestion points: Video footage metadata and timeline clip sequences analyzed during the DERIVE phase in
SKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded content are provided.
- Capability inventory: Executes video manipulation commands including
setSpeed,setColor,snapToBeat, andapplyFilterPresetvia tool calls. - Sanitization: No sanitization of clip metadata or user-supplied project titles is described.
- [SAFE]: External references in
references/sources.mdpoint to established filmmaking educational resources and industry-standard blogs.
Audit Metadata