ui-ux-improve
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests untrusted data that could influence the agent's behavior.
- Ingestion points: The agent reads local project files (e.g.,
package.json,**/*.tsx) and retrieves external content from the internet via theWebSearchtool. - Boundary markers: There are no explicit delimiters or instructions provided to ensure the agent ignores or sanitizes potential commands embedded within the code or web content it analyzes.
- Capability inventory: The agent has the ability to read project files, perform web searches, invoke specialized sub-agents, write a markdown report to the project root, and modify project code when in
implementmode. - Sanitization: No validation or sanitization routines are specified for the data gathered from the project or external sources before it is used to formulate recommendations or execute changes.
Audit Metadata