ubiquitous-language
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from PRD files and the codebase to extract terminology.
- Ingestion points: Reads
*-prd.mdand*-scope.mdfiles from the./plans/directory and searches the codebase for database models, API definitions, and type signatures. - Boundary markers: No explicit delimiters or instructions are provided to the agent to isolate the processed content from its instructions.
- Capability inventory: The skill can perform codebase-wide searches and write files to the
./plans/directory. - Sanitization: Extracted content is not sanitized or validated before being processed by the agent.
Audit Metadata