speaker-cutout
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: Comprehensive security analysis of the skill instructions and scripts found no evidence of malicious intent or hidden vulnerabilities.
- [COMMAND_EXECUTION]: The skill facilitates video layout planning through
scripts/speaker_layer.py. The script includes defensive programming practices, specifically validating all numeric parameters (scale, anchors) and configuration modes to ensure they are within safe operational limits before generating string outputs. - [INDIRECT_PROMPT_INJECTION]: The skill exposes a surface for parameter interpolation during the layout planning phase. However, a robust validation chain is implemented: (1) Ingestion: parameters enter through CLI arguments; (2) Boundaries: explicit numeric and finite-value checks; (3) Capabilities: strictly limited to generating filtergraph strings; (4) Sanitization: type-casting and range-checking of all external values. This effectively prevents the injection of malicious FFmpeg parameters.
Audit Metadata