glossary
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs legitimate domain analysis by extracting terminology from PRDs and comparing it with existing codebase naming conventions. All operations are restricted to the local file system within the project context.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes external content from the codebase and PRD files. However, given its primary purpose is terminology extraction and the output is limited to a local markdown glossary, the risk is minimal.
- Ingestion points: Reads PRD files (
*-prd.md), scope documents (*-scope.md), and codebase files (models, API routes, type definitions) inSKILL.md. - Boundary markers: None specified to delimit ingested content from instructions.
- Capability inventory: Performs file reads and writes (via
SKILL.mdinstructions) to the./plans/directory. - Sanitization: No explicit sanitization or escaping of ingested terminology is mentioned before writing to the glossary template.
Audit Metadata