ubiquitous-language

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface as it processes conversation history to extract terms.
  • Ingestion points: Conversation history processed during the term extraction and formalization steps.
  • Boundary markers: Absent; no specific delimiters are used to isolate user-provided conversation text from the instructions.
  • Capability inventory: File-write access to UBIQUITOUS_LANGUAGE.md within the working directory.
  • Sanitization: Absent; domain terms are extracted and written directly to the markdown file without explicit validation or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 01:04 PM