react-debugging
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by ingesting untrusted data from external web applications during the debugging process.
- Ingestion points: Untrusted data enters the agent context through tools like
browser-devtools-cli react get-component-for-elementandcontent get-as-html, which retrieve React component props, state, and HTML content from the browser. - Boundary markers: The instructions do not define clear delimiters or specify that the agent should ignore instructions potentially embedded within the web content or React component data.
- Capability inventory: The agent has access to the
browser-devtools-clitool, which can navigate to URLs and execute browser-based commands. - Sanitization: There is no evidence of sanitization, validation, or escaping of the data retrieved from the web browser before it is processed by the agent.
Audit Metadata