creator-productivity
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill manages and retrieves project context from user-controlled local files.\n
- Ingestion points: The agent reads context from
TASKS.md,CREATOR.md, and project briefs within thecreator-memory/directory.\n - Boundary markers (absent): The instructions lack specific delimiters or instructions for the agent to ignore potentially malicious embedded content within these files.\n
- Capability inventory: The skill is authorized to read and write to the local filesystem for initializing templates and updating task/memory logs.\n
- Sanitization (absent): No content validation or sanitization mechanisms are specified for handling the data from the creative memory system.
Audit Metadata