the-scene-composer
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill reads from local configuration files, specifically
.agents/product-context.mdandreferences/scene-composition.md. This access is confined to the agent's project environment to retrieve brand guidelines and scene library data, and no sensitive information is exfiltrated to external domains. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local reference files, which represents a potential attack surface if those files contain malicious instructions. However, the skill possesses no high-risk capabilities such as file writing, network requests, or command execution.
- Ingestion points:
.agents/product-context.mdandreferences/scene-composition.md(SKILL.md). - Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions for the data read from these files.
- Capability inventory: The skill is limited to generating formatted text output; it lacks access to system tools or network protocols.
- Sanitization: No explicit sanitization or filtering of the local file content is performed prior to processing.
Audit Metadata