ubiquitous-language

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests conversation history to identify domain terms. This creates a surface for indirect prompt injection where an attacker could influence the glossary content or attempt to inject instructions through conversation data.\n- Ingestion points: Current conversation history (referenced in SKILL.md).\n- Boundary markers: Absent for the conversation scanning process.\n- Capability inventory: File system write access (UBIQUITOUS_LANGUAGE.md), sequentialthinking and context7 MCP loop capabilities.\n- Sanitization: The skill includes a protocol to redact secrets and PII from context shared with subagents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 01:39 PM
Security Audit — agent-trust-hub — ubiquitous-language