frontend-ui-ux
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it interpolates user-controlled data into its execution flow.
- Ingestion points: User input is ingested via the
{{ARGUMENTS}}placeholder inSKILL.md, specifically within thedelegatefunction call and as a trailing instruction. - Boundary markers: The skill lacks explicit delimiters or instructions to the agent to ignore or treat the
{{ARGUMENTS}}content as untrusted data. - Capability inventory: The skill has the ability to delegate tasks to other agents and invoke MCP tools such as
mcp__g__ask_gemini. - Sanitization: There is no evidence of filtering, escaping, or validation applied to the input before it is processed by the agent.
Audit Metadata