ubiquitous-language
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted conversation history to generate a glossary, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads the current conversation history and the existing
UBIQUITOUS_LANGUAGE.mdfile to update domain terminology. - Boundary markers: The instructions lack explicit boundary markers or delimiters to instruct the agent to ignore potential commands embedded within the domain terminology being processed.
- Capability inventory: The skill utilizes file-read and file-write capabilities to manage the
UBIQUITOUS_LANGUAGE.mdfile in the working directory. - Sanitization: There are no specified sanitization or validation steps to filter extracted content before it is persisted to the local filesystem.
Audit Metadata