video-trimmer
Pass
Audited by Gen Agent Trust Hub on Nov 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements standard video processing functionality without suspicious network activity, credential handling, or code obfuscation.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface where it processes external data in the form of a JSON segments file.
- Ingestion points:
scripts/trim_multiple.pyreads segment definitions from an external JSON file. - Boundary markers: No explicit boundary markers are used in the instructions to separate data from control logic.
- Capability inventory: The skill leverages FFmpeg via a shared wrapper to perform file operations.
- Sanitization: Timestamps are validated and converted to floating-point seconds, and durations are clamped to valid video bounds, preventing typical injection attacks through these parameters.
Audit Metadata