ubiquitous-language

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a documentation tool that extracts domain concepts and saves them to a local markdown file. It does not perform network requests, access sensitive credentials, or execute commands.
  • [PROMPT_INJECTION]: The skill processes untrusted conversation data and reads from a local file, creating a surface for indirect prompt injection. However, the risk is negligible as the skill's capabilities are limited to writing static markdown documentation.
  • Ingestion points: Conversation history and the local UBIQUITOUS_LANGUAGE.md file.
  • Boundary markers: Lacks specific delimiters to isolate user-provided content from instructions.
  • Capability inventory: Local file system access is limited to writing and updating a single markdown file.
  • Sanitization: No explicit content validation or escaping is defined for the extracted terminology.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 05:07 AM
Security Audit — agent-trust-hub — ubiquitous-language