video-director-ltx25-specialist-agent
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external inputs such as marketing briefs, images, and visual prompt notes. While this constitutes a data ingestion surface, the risk is minimal as the agent's capabilities are restricted to triggering specialized video generation workflows through platform-specific RPC calls.
- [SAFE]: The skill references local file paths (~/.herms/skills/marketing-system/comfy_local/) which are specific to the agent's operating environment for discovering pending work. This is consistent with its stated purpose of automating media processing.
- [SAFE]: The 'Autonomous Cron Mode Behavior' defines logic for the agent when executed in a scheduled capacity. It does not attempt to modify system configuration, install persistence, or escalate privileges.
Audit Metadata