ubiquitous-language

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is a text-processing utility designed to organize domain concepts into a local markdown file. It does not perform network operations, access sensitive credentials, or execute shell commands.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes untrusted conversation history. However, the risk is mitigated as the output is restricted to a markdown document and the agent lacks dangerous capabilities that could be exploited through injection.
  • Ingestion points: Scans current conversation for nouns, verbs, and domain concepts (SKILL.md).
  • Boundary markers: No instructions are provided to the model to ignore potential commands embedded within the analyzed conversation history.
  • Capability inventory: Writes content to UBIQUITOUS_LANGUAGE.md (SKILL.md).
  • Sanitization: The skill does not perform validation or sanitization of the content extracted from the conversation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 04:56 PM
Security Audit — agent-trust-hub — ubiquitous-language