alterlab-genai-camera-director
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its workflow for processing project files.
- Ingestion points: The skill reads existing project files, specifically scripts, shot lists, and storyboards, to maintain creative continuity (SKILL.md).
- Boundary markers: There are no instructions or delimiters provided to the agent to distinguish between narrative content and potentially malicious instructions within those project files.
- Capability inventory: The skill is capable of writing multiple production-related files to the local project directory and performing web searches (SKILL.md).
- Sanitization: The instructions do not define any sanitization or verification steps for the data ingested from the external project files.
Audit Metadata