skills/agentskillexchange/skills/Turn a plain-language brief into a multi-step video production pipeline with OpenMontage/Gen Agent Trust Hub
Turn a plain-language brief into a multi-step video production pipeline with OpenMontage
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFENO_CODEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and metadata. There are no executable scripts (.sh, .py, .js), shell commands, or tool-granting configurations (such as allowed-tools) present in the file.
- [EXTERNAL_DOWNLOADS]: The skill contains links to an external GitHub repository (calesthio/OpenMontage) and raw documentation (raw.githubusercontent.com). These are informational references for the user and do not initiate automated downloads or remote code execution during skill loading.
- [INDIRECT_PROMPT_INJECTION]: The skill's described functionality involves processing untrusted external data such as user-provided video briefs.
- Ingestion points: Processes "plain-language briefs" and "reference videos" as inputs for the production pipeline (SKILL.md).
- Boundary markers: None present in the skill definition to delimit user content from instructions.
- Capability inventory: The documentation mentions capabilities for "asset generation," "scripting," and a "render pipeline."
- Sanitization: No specific sanitization or input validation logic is defined within the skill metadata.
Audit Metadata