aiox-analyst

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Node.js script located at .aiox-core/development/scripts/generate-greeting.js to initialize the agent persona.
  • [PROMPT_INJECTION]: The activation protocol creates a surface for indirect instructions by loading a persona definition from an external local file (.aiox-core/development/agents/analyst.md).
  • Ingestion points: Protocol step 1 references .aiox-core/development/agents/analyst.md as the source of truth.
  • Boundary markers: No explicit delimiters or ignore-instructions markers are present in the activation steps.
  • Capability inventory: The skill has the capability to execute local Node.js scripts.
  • Sanitization: No sanitization or validation of the loaded file's content is described in the protocol.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 11:44 PM
Security Audit — agent-trust-hub — aiox-analyst