tanstack-ai-memory-honcho
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill describes a process where data from the Honcho service is retrieved and placed into the system prompt, establishing an indirect prompt injection vulnerability surface.
- Ingestion points: The
recallfunction retrieves synthesized answers from the Honcho platform. - Boundary markers: The instructions lack delimiters or isolation rules for the injected memory content.
- Capability inventory: The skill relies on the
@honcho-ai/sdkfor external API communication. - Sanitization: No sanitization or validation of the retrieved memory data is specified.
- [EXTERNAL_DOWNLOADS]: The documentation requires installation of
@tanstack/ai-memoryand@honcho-ai/sdkpeer dependencies. - [NO_CODE]: This skill provides only instructions and documentation, with no executable scripts or tool definitions included.
Audit Metadata