idea-refiner

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [Data Integration Analysis]: The skill is designed to interact with 'Work IQ', a feature used for accessing internal workspace information. This is a standard capability for productivity tools within the intended platform, allowing the agent to provide context-aware refinements based on internal facts.
  • [Indirect Prompt Injection Surface]: The skill's core function involves processing user-provided drafts and plans, which represents a potential surface for indirect instructions.
  • Ingestion points: The agent ingests user-supplied plans, decisions, or drafts to perform its refinement task.
  • Boundary markers: There are no explicit delimiters or specific instructions to ignore embedded commands within the user's draft content.
  • Capability inventory: The skill is limited to conversational refinement and questioning; it does not contain logic for file system access, network operations, or shell command execution.
  • Sanitization: User input is processed directly into the refinement workflow without specific sanitization steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 11:55 PM
Security Audit — agent-trust-hub — idea-refiner