ui-component-selector
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes content from an external domain (The Component Gallery), which introduces a surface for indirect prompt injection attacks.
- Ingestion points: According to Step 3 of the workflow in
SKILL.md, the agent retrieves candidate names, alternate names, descriptions, and examples from external pages oncomponent.gallery. - Boundary markers: The instructions do not provide explicit boundary markers or 'ignore' instructions to prevent the agent from following malicious commands that might be embedded in the retrieved external descriptions.
- Capability inventory: Across
SKILL.md, the agent is granted read-only access to sensitive project evidence (dependencies, lockfiles, and configuration files) and is authorized to implement code changes when requested. - Sanitization: There are no specified procedures for validating, filtering, or sanitizing the content fetched from the external documentation site before it is used to influence the agent's logic.
Audit Metadata