ubiquitous-language
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted conversation history to extract terms and formalize a glossary, creating a surface for indirect prompt injection where malicious input could influence the glossary content.
- Ingestion points: Scans current conversation for concepts.
- Boundary markers: None present.
- Capability inventory: Local file system read and write access to 'UBIQUITOUS_LANGUAGE.md'.
- Sanitization: None specified.
Audit Metadata