remember
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill manages a long-term memory system (
remindb) which stores and retrieves information for the agent. This creates a vulnerability surface for indirect prompt injection attacks. - Ingestion points: The skill ingests user-provided text, decisions, and facts to be saved in the database via the
memorizecommand (SKILL.md). - Boundary markers: No specific delimiters or instructions to ignore embedded commands within stored data are defined in this routing skill.
- Capability inventory: The system uses
MemorySearchandMemoryFetchto bring stored content back into the active agent context to inform future responses and actions. - Sanitization: The instructions do not specify any sanitization or validation of the content before it is stored or after it is retrieved.
Audit Metadata