ui-translation
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted natural language UI descriptions to generate functional code.
- Ingestion points: Natural language UI descriptions provided by the user (SKILL.md).
- Boundary markers: The skill lacks explicit delimiters or instructions to treat user-provided descriptions as data to prevent the agent from following instructions embedded within those descriptions.
- Capability inventory: The skill generates React/TypeScript code and recommends component implementations, which could be exploited if malicious instructions are hidden in the input descriptions.
- Sanitization: There is no specified logic for sanitizing, escaping, or validating the user-provided descriptions before they are interpreted for code generation.
Audit Metadata