remember
Pass
Audited by Gen Agent Trust Hub on May 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides high-level coordination instructions and contains no scripts, network access, or sensitive file operations.- [PROMPT_INJECTION]: The skill manages a data ingestion surface for long-term memory, which allows for indirect prompt injection. This is considered a standard feature for this type of skill.
- Ingestion points: Processes user-provided text for storage and retrieval via the remindb server (SKILL.md).
- Boundary markers: None specified in this router skill; boundary management is handled by downstream tools.
- Capability inventory: Directs the agent to tools for memory writing and searching (
MemoryWrite,MemorySearch,MemoryFetch). - Sanitization: No specific sanitization or validation logic is defined at the coordination level.
Audit Metadata