memory-research

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious code or patterns detected. The skill uses a structured research and storage workflow that relies on standard search and note-taking tools.
  • [PROMPT_INJECTION]: This skill handles external data from web searches, which presents a surface for indirect prompt injection. This is mitigated by the structured workflow and the requirement for user approval before any information is permanently stored. Ingestion point: Web research results (Step 1). Boundary markers: Data is processed into a structured Markdown summary (Step 3). Capability inventory: Includes search_notes, write_note, and edit_note for knowledge management. Sanitization: Relies on user verification and explicit approval (Step 4) before storage.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 07:57 PM