ubiquitous-language

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's primary function is text analysis and local file management. It writes to 'UBIQUITOUS_LANGUAGE.md' in the working directory and does not interact with external networks or sensitive system files.
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it processes data from user conversations.
  • Ingestion points: Analyzes the current conversation history for domain-relevant nouns, verbs, and concepts.
  • Boundary markers: None; the skill does not use delimiters to isolate untrusted conversation data from its processing logic.
  • Capability inventory: Capabilities are limited to local file creation and writing to 'UBIQUITOUS_LANGUAGE.md'.
  • Sanitization: No validation or sanitization of the extracted terminology is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 01:57 AM
Security Audit — agent-trust-hub — ubiquitous-language