glossary-builder
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No security issues detected. The skill provides instructions for terminology management using natural language and does not include any executable components or network requests.
- [NO_CODE]: The skill consists exclusively of markdown instructions and does not include any scripts, configuration files, or executable code.
- [PROMPT_INJECTION]: The skill is designed to process untrusted source material (UI text, documentation) to extract terms. While this constitutes an ingestion point for indirect prompt injection, the risk is negligible because the skill lacks access to any sensitive tools, network functions, or file system operations. 1. Ingestion points: Source material and domain-specific text provided by the user in context of SKILL.md. 2. Boundary markers: None present. 3. Capability inventory: No executable capabilities or tool permissions are requested or used. 4. Sanitization: No input sanitization or validation logic is defined.
Audit Metadata