ubiquitous-language
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core function of ingesting untrusted conversation data.
- Ingestion points: The skill instructions direct the agent to 'Scan the conversation' for domain-relevant nouns, verbs, and concepts (SKILL.md).
- Boundary markers: The instructions lack specific delimiters or instructions to ignore embedded commands within the scanned conversation text.
- Capability inventory: The skill has the capability to write to the local file system by creating or updating the
UBIQUITOUS_LANGUAGE.mdfile (SKILL.md). - Sanitization: There are no specified mechanisms to sanitize, validate, or escape the content extracted from the conversation before it is persisted to the file system.
Audit Metadata