agentmemory-rest-api
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by providing mechanisms to retrieve and process stored data from a memory server.\n
- Ingestion points: Data enters the agent's context through multiple endpoints including
/agentmemory/memories,/agentmemory/smart-search, and/agentmemory/context.\n - Boundary markers: The documentation does not specify the use of delimiters or instructions to ignore embedded commands to separate retrieved memory content from the agent's primary instructions.\n
- Capability inventory: The agent is instructed to interact with the API using HTTP methods to read and search memory, allowing stored content to influence agent behavior.\n
- Sanitization: No sanitization or validation routines for external memory content are described in the provided reference material.
Audit Metadata