studio-director
Pass
Audited by Gen Agent Trust Hub on Nov 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user data, creating a surface for indirect prompt injection.
- Ingestion points: The skill takes a "raw video idea" and "past scripts or videos" from the user to define the project brief and voice (Step 0 in
SKILL.md). - Boundary markers: The instructions lack explicit boundary markers or delimiters to isolate user-provided content from the agent's operational instructions.
- Capability inventory: The skill possesses file-writing capabilities (e.g., creating
brief.md,script.md,shotlist.md) and orchestrates the execution of multiple sub-skills and local tools. - Sanitization: There is no evidence of sanitization, filtering, or validation of the user-provided input before it is used to generate project documentation and scripts.
Audit Metadata