ubiquitous-language
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes codebase structural files like database schemas, API contracts, and domain layer code to generate the thesaurus. This creates a surface for indirect prompt injection where malicious instructions could be embedded in codebase comments or metadata that the agent processes during thesaurus generation.
- Ingestion points: DB schemas, API specs, and source code files (SKILL.md, generating-thesaurus.md).
- Boundary markers: The skill does not explicitly define delimiters to separate codebase content from agent instructions during ingestion.
- Capability inventory: The agent has access to Write, Edit, and Bash tools, which could potentially be triggered by instructions found in scanned files.
- Sanitization: No sanitization is performed on the extracted domain terms before inclusion in the thesaurus or project instructions.
- [COMMAND_EXECUTION]: The skill utilizes tools like Bash, Grep, and Glob to perform naming audits and term harvesting across the repository. This includes executing shell commands to locate files and scan for specific patterns to ensure compliance with the defined thesaurus (naming-audit.md).
Audit Metadata