creative-write

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes instructions and context from various external local files to determine its generation behavior and workflow. Ingestion points: Files such as .creative/config.yaml, domain.yaml, write-guide.md, and project-specific planning documents. Boundary markers: The instructions do not define delimiters or specific safety prompts to differentiate between control logic and data in these files. Capability inventory: The agent is granted Read, Write, Edit, Glob, and Grep capabilities. Sanitization: No validation or escaping of the content loaded from these external files is mentioned.
  • [DYNAMIC_EXECUTION]: The skill performs dynamic path calculation to load domain-specific configurations. Evidence: The DOMAIN_DIR path is computed using a domain variable retrieved from the .creative/config.yaml file without explicit validation, which could allow for path traversal if the value is maliciously crafted.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 11:40 AM