ubiquitous-language

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is focused on documentation and terminology management. It reads and writes to a single local file (UBIQUITOUS_LANGUAGE.md) and does not initiate network requests or execute arbitrary code.
  • [PROMPT_INJECTION]: While the skill processes untrusted user input from the conversation, it does not demonstrate any patterns of direct prompt injection or attempts to override system safety protocols. It creates a minor surface for indirect prompt injection common to any data-processing skill.
  • Ingestion points: The skill reads the current conversation history and the existing UBIQUITOUS_LANGUAGE.md file (SKILL.md).
  • Boundary markers: The instructions do not define strict delimiters to isolate user-provided text from the agent's internal instructions.
  • Capability inventory: The agent is instructed to write and update a local markdown file (UBIQUITOUS_LANGUAGE.md) using standard file system tools.
  • Sanitization: There are no explicit instructions to sanitize or validate user-provided terms or definitions before committing them to the glossary file.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 10:24 AM
Security Audit — agent-trust-hub — ubiquitous-language