ubiquitous-language
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for documentation and terminology management. It reads conversation history and writes to a local Markdown file (UBIQUITOUS_LANGUAGE.md).
- [COMMAND_EXECUTION]: Mentions of command names like
execandcopyInare located within a Markdown example section describing terminology usage. These are not instructions for the agent to execute shell commands. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from the conversation history to generate a structured glossary.
- Ingestion points: Conversation history and existing
UBIQUITOUS_LANGUAGE.md(referenced in SKILL.md). - Boundary markers: The agent is provided with a specific Markdown structure to follow, which acts as a constraint, though explicit security delimiters are absent.
- Capability inventory: File writing to
UBIQUITOUS_LANGUAGE.md(specified in SKILL.md). - Sanitization: None detected. The skill summarizes input directly into the documentation format.
Audit Metadata