ubiquitous-language
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user input from the active conversation and the local glossary file, which constitutes an indirect prompt injection surface.
- Ingestion points: Processes content from the live conversation and reads the
UBIQUITOUS_LANGUAGE.mdfile from the working directory during re-runs. - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when processing external data.
- Capability inventory: Limited to reading and writing the
UBIQUITOUS_LANGUAGE.mdfile. It does not have access to network operations, subprocess execution, or administrative system paths. - Sanitization: The skill does not implement sanitization or validation of the domain terms extracted from the conversation.
Audit Metadata