chatcrystal-debug-recall
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process historical data ("memories") via the
recall_for_tasktool, which constitutes a vulnerability surface if the historical content contains malicious instructions. - Ingestion points: The skill receives data from the
recall_for_taskMCP tool as specified in the workflow section ofSKILL.md. - Boundary markers: The instructions provide a behavioral constraint ("Use recalled memories to sharpen diagnosis, not to skip verification in the current environment"), which serves as a mitigation but not a complete boundary.
- Capability inventory: The skill operates within a debugging context where the agent likely has access to file system operations, command execution, and build tools.
- Sanitization: There is no evidence of automated sanitization, validation, or filtering applied to the memories returned by the tool before they are processed by the agent.
Audit Metadata