ui-doctor
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted application source code (e.g.,
.tsx,.jsx,.ts,.jsfiles) to perform UI audits. This creates a surface where malicious instructions embedded in comments or strings within the code being audited could attempt to influence the agent's behavior or output. - Ingestion points: Reads files in the
src/directory and application entry points (e.g.,main.tsx,index.tsx) as specified in the 'Audit Scope' section ofSKILL.md. - Boundary markers: The instructions lack specific boundary markers or requirements for the agent to treat code content as untrusted data when generating the audit report.
- Capability inventory: The skill primarily performs file read operations and generates text-based reports. It does not explicitly call for subprocess execution, file writes, or network operations, though it relies on the agent's underlying toolset.
- Sanitization: No sanitization or escaping of the ingested code content is described before it is processed for the audit report.
Audit Metadata