recipe-curriculum-audit

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE] (SAFE): The skill consists entirely of markdown instructions and does not include any executable code, scripts, or package dependencies.
  • [Indirect Prompt Injection] (LOW): The skill instructs the agent to ingest and inspect external recipe configuration files. 1. Ingestion points: recipe config and related files. 2. Boundary markers: None. 3. Capability inventory: No executable scripts or tools are provided in this skill. 4. Sanitization: None. While an attacker could place instructions in a config file, the lack of tool capabilities minimizes the risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:38 PM