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.md and references/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.md and references/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
Risk Level
SAFE
Analyzed
Aug 14, 2026, 12:03 PM