chatcrystal-task-recall

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of external data via the ChatCrystal memory system, creating a surface for indirect prompt injection.
  • Ingestion points: Data enters the agent's context through project_memories and global_memories fetched by the recall_for_task tool as described in SKILL.md.
  • Boundary markers: The instructions do not define clear delimiters or boundary markers to isolate recalled memories from the primary task instructions.
  • Capability inventory: The skill instructs the agent to perform substantive actions such as implementation, refactoring, and configuration, which could be subverted by malicious instructions embedded in the recalled data.
  • Sanitization: There are no verification or sanitization steps mentioned to process the data retrieved from the memory store before implementation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 03:08 PM
Security Audit — agent-trust-hub — chatcrystal-task-recall