environment-establishing-shot-planner

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external scene briefs and user-provided locale/weather data, which could potentially contain malicious instructions intended to influence the agent's output.
  • Ingestion points: Processes input briefs from intent-to-3d-brief-writer and user-defined parameters in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the processed data.
  • Capability inventory: The skill is limited to generating text-based scene plans and flagging assets for downstream tools; it explicitly prohibits Blender execution or arbitrary Python interfaces.
  • Sanitization: There is no evidence of input validation or sanitization for the provided scene descriptions or parameters.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 07:02 PM