ubiquitous-language
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted data from the conversation history to generate its output. This is a low-risk finding inherent to the skill's purpose as a text-processing utility.
- Ingestion points: The current conversation history is processed to identify domain terms, as specified in the "Process" section of
SKILL.md. - Boundary markers: Absent; the skill does not define specific delimiters to distinguish between conversation content and instructions.
- Capability inventory: The skill is authorized to perform local file system writes (specifically creating and updating
UBIQUITOUS_LANGUAGE.md). - Sanitization: Absent; the skill extracts terms directly from user-provided text without specialized filtering for command-like structures or markdown injection, though the impact is limited to the content of the generated file.
Audit Metadata