search
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and displays data from an external memory storage, which serves as an ingestion point for potentially untrusted data that could influence agent behavior.\n
- Ingestion points: Search results returned by the
mem0_memorytool (e.g., memory content and categories).\n - Boundary markers: The skill does not implement specific delimiters or safety instructions to distinguish search results from the agent's primary instructions.\n
- Capability inventory: The skill searches and displays memory content to the agent context.\n
- Sanitization: The skill does not specify any sanitization, filtering, or validation of the content retrieved from the memory store.
Audit Metadata