ie-retrieve-memory

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses a set of specialized tools (e.g., wpsnote.search_notes, find_tags, read_blocks) to interact with the user's note library. All operations are confined to retrieval and structured summarization within the platform's ecosystem.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it ingests and processes user-generated note content that may contain untrusted instructions. This is a standard risk for retrieval-based tasks.
  • Ingestion points: User note content and metadata retrieved via tools defined in SKILL.md.
  • Boundary markers: None explicitly defined in the retrieval instructions.
  • Capability inventory: Read-only access to search, list, and read note content (SKILL.md).
  • Sanitization: No explicit validation or filtering of note content is described in the prompt logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 04:00 AM
Security Audit — agent-trust-hub — ie-retrieve-memory