icons8-design
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of external content, including UI source code and user-facing strings, which presents a surface for indirect prompt injection.
- Ingestion points: The skill analyzes UI code, components, and user-facing strings (e.g., buttons, labels, error states) provided during a design review pass.
- Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions that might be hidden within the UI code or text content being reviewed.
- Capability inventory: The skill coordinates actions across multiple specialized sub-skills and interacts with the Icons8 MCP to perform file and asset modifications.
- Sanitization: The skill does not specify any sanitization or validation routines for the external data it ingests before passing it to the agent's context.
Audit Metadata