mem0-context-loader
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from previous user sessions, creating a surface where malicious instructions could be reintroduced into the active agent context.
- Ingestion points: Memory content retrieved via the search_memories tool from the mem0 platform (SKILL.md).
- Boundary markers: The skill structures output using a context-loader header and list markers, but lacks explicit boundary instructions telling the agent to treat the memory contents as untrusted data or to ignore embedded commands.
- Capability inventory: The skill itself is restricted to read-only operations and text output, but the agent receiving this context may have other tools (e.g., shell access) that could be targeted by an injection.
- Sanitization: No sanitization, filtering, or escaping is applied to the content retrieved from the memory database before it is presented to the agent.
Audit Metadata