create-moment
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a standard workflow for integrating with the Montage video platform using dedicated tools. No malicious patterns, suspicious downloads, or credential exposures were detected.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it reads and processes external data such as video transcripts and visual analysis content to make logic-based decisions. This surface is consistent with the skill's primary function and is mitigated by the model's internal safety guardrails.\n
- Ingestion points:
get_transcript,get_video_analysis, andget_video_corpusinSKILL.md.\n - Boundary markers: Not explicitly defined.\n
- Capability inventory: Project management and clip creation via Montage MCP tools.\n
- Sanitization: None identified; the skill relies on model-driven parsing of timestamps and text content.
Audit Metadata