ubiquitous-language

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs expected file operations on 'UBIQUITOUS_LANGUAGE.md' to maintain a domain glossary, which is consistent with its described purpose and author context.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection via the processing of untrusted conversation data.\n
  • Ingestion points: Current conversation history and the existing 'UBIQUITOUS_LANGUAGE.md' file.\n
  • Boundary markers: Absent; there are no explicit delimiters or safety instructions provided to the agent to distinguish between valid domain terms and potentially malicious instructions embedded in the conversation.\n
  • Capability inventory: The skill has the capability to read from and write to the local file 'UBIQUITOUS_LANGUAGE.md'.\n
  • Sanitization: Absent; the skill does not explicitly validate or sanitize the content extracted from the conversation before writing it to the glossary file.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 07:58 AM