captions-overlay
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided source material and inputs, creating a potential surface for instructions embedded in processed data.
- Ingestion points: Source material and existing project files referenced in the workflow (SKILL.md).
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the source material.
- Capability inventory: The skill can create artifacts, render/preview output, and execute external tool calls via sandbase_run (references/sandbase-api-map.md).
- Sanitization: The instructions do not specify sanitization or validation of the content extracted from source materials.
Audit Metadata