spanish-cooking-expert

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Overall Security (SAFE): No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected. The skill is composed of static markdown documentation.
  • Indirect Prompt Injection (SAFE): The skill contains instructions for data ingestion in modules/research-checklist.md which constitutes a vulnerability surface. 1. Ingestion points: The research checklist recommends using web research tools like adn_skills. 2. Boundary markers: Absent from the workflow instructions. 3. Capability inventory: No dangerous capabilities such as subprocess calls, exec/eval, file-write, or network operations are present in any of the skill files. 4. Sanitization: Absent. Given the lack of dangerous capabilities and the intended primary purpose of the skill, this is considered low risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:28 PM