memory-lifecycle
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates on user-generated notes, which serves as a potential vector for indirect prompt injection.
- Ingestion points: External data is ingested through the search_notes and edit_note tools while identifying and updating note content.
- Boundary markers: There are no instructions for using delimiters or boundary markers to prevent the agent from following instructions embedded within the notes.
- Capability inventory: The skill possesses capabilities to move files (move_note) and modify their contents (edit_note) within the local memory store.
- Sanitization: The skill lacks explicit sanitization or validation logic for the content it processes and updates.
Audit Metadata