ubiquitous-language
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core logic of persisting conversation-derived content to a local file that is subsequently re-ingested into the agent's context.\n
- Ingestion points: The skill scans the current conversation history for domain-relevant terms to extract (SKILL.md).\n
- Boundary markers: The skill does not define specific delimiters or instructions to ignore malicious commands embedded within the extracted domain terms when reading the glossary file.\n
- Capability inventory: The skill possesses the ability to write to and read from
UBIQUITOUS_LANGUAGE.mdin the working directory (SKILL.md).\n - Sanitization: There is no evidence of sanitization, validation, or escaping of the conversation content before it is stored in the glossary or re-read by the agent.
Audit Metadata