film-crew
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data, including video concepts, failed prompts, and clip descriptions, which are used to generate planning documents and prompts.
- Ingestion points: User input provided during Plan, Fix, and Review modes (SKILL.md).
- Boundary markers: The skill employs a structured multi-role pipeline that implicitly separates different processing steps, although it does not use explicit security delimiters for input data.
- Capability inventory: The skill identifies capabilities for writing to local files (SHOT_LIST.md) and generating text output based on the crew roles.
- Sanitization: The 'Script Supervisor' (references/roles/script-supervisor.md) and 'Unslop' (references/unslop.md) modules provide functional sanitization by checking for continuity, feasibility, and quality of the generated prompts.
- [SAFE]: No malicious patterns such as credential exfiltration, obfuscated code, persistence mechanisms, or unauthorized privilege escalation were detected. All external URL references point to the author's own repository for documentation and asset purposes.
Audit Metadata