mlt
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
meltcommand-line utility to process media graphs and render XML. This is the intended purpose of the skill for multitrack video processing and playback. - [INDIRECT_PROMPT_INJECTION]: The skill reads external reference files (MLT_TOOLKIT.md) and processes MLT XML files. While these represent ingestion points for untrusted data, the skill is scoped to media processing operations within the MLT framework, and no capabilities for arbitrary code execution or network exfiltration were identified.
- Ingestion points: Reads
../../references/MLT_TOOLKIT.mdand processes generated/loaded MLT XML. - Boundary markers: None explicitly mentioned for XML content.
- Capability inventory: Execution of
meltfor media querying, rendering, and playback. - Sanitization: Not explicitly mentioned, but operations are restricted to the MLT service graph logic.
Audit Metadata