tanstack-ai-memory-honcho
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external memory service (Honcho) and injects it into the system prompt, which is a standard surface for indirect prompt injection.
- Ingestion points: The
recallfunction retrieves synthesized answers from the Honcho peer-to-peer message store (SKILL.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are described in the setup.
- Capability inventory: The provided configuration does not include file system writes or subprocess execution capabilities.
- Sanitization: The documentation does not specify sanitization or validation of the memory content before it is injected into the prompt.
Audit Metadata