mem0
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the mem0ai library and CLI tools from official package registries like PyPI and NPM. These are established dependencies required for the skill's stated purpose of providing memory management capabilities.
- [PROMPT_INJECTION]: The skill describes a memory layer architecture that processes and retrieves arbitrary external data, which creates a surface for indirect prompt injection attacks.
- Ingestion points: External data is ingested into the agent's context through the
memory.add()method as documented in SKILL.md. - Boundary markers: The instructions lack specific markers or guidelines to prevent the agent from treating data retrieved from memory as authoritative instructions.
- Capability inventory: The skill's environment is configured with access to powerful tools including
Bash,Write,Edit,Read,Glob, andGrep(as listed in allowed-tools). - Sanitization: No explicit sanitization or validation steps are provided for the content stored in or retrieved from the memory layer.
Audit Metadata