define-domain

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to manage documentation (CONTEXT.md and ADRs). It does not request or use tools for network access, arbitrary code execution, or credential management.
  • [DATA_EXPOSURE]: The skill accesses project documentation and source code to identify and cross-reference domain terms. This access is consistent with its stated purpose of ensuring the glossary and implementation do not disagree.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it reads untrusted project content (code and Markdown docs) to perform its tasks.
  • Ingestion points: Project source code, CONTEXT.md, and ADR files in docs/adr/ (SKILL.md).
  • Boundary markers: None explicitly defined for interpolated data.
  • Capability inventory: The skill is limited to writing documentation updates to CONTEXT.md and creating/archiving files in docs/adr/.
  • Sanitization: None specified for external content processed during glossary audits.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 12:39 PM
Security Audit — agent-trust-hub — define-domain