omnicaptions-LaiCut
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
omni-captions-skillspackage from a vendor-provided repository athttps://lattifai.github.io/pypi/simple/. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted media and caption files, creating a surface for indirect instructions. 1. Ingestion points: Processes media and caption files provided as CLI arguments. 2. Boundary markers: No delimiters or ignore-instruction markers are specified for caption content. 3. Capability inventory: The skill uses
Bashfor command execution and has file system access. 4. Sanitization: No sanitization of input text is documented.
Audit Metadata