chatcrystal-task-recall
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves context from project_memories and global_memories via the recall_for_task tool to guide development activities.
- Ingestion points: Data enters the context via the recall_for_task tool as described in SKILL.md.
- Boundary markers: The instructions do not specify any boundary markers or instructions for the agent to ignore or isolate embedded instructions within the recalled memory.
- Capability inventory: The agent is authorized to perform substantive implementation, refactoring, and configuration tasks based on the ingested data.
- Sanitization: No sanitization or validation logic is defined for the content retrieved from the memory system.
Audit Metadata