react-debugging
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates indirect prompt injection by ingesting and processing untrusted data from external web pages.
- Ingestion points: The skill reads external data using
get-as-htmlandget-console-messagestools. - Boundary markers: No boundary markers or 'ignore' instructions are used to separate web content from system prompts.
- Capability inventory: The skill possesses capabilities to navigate the browser and manage sessions using
browser-devtools-cli. - Sanitization: No sanitization or validation of the retrieved HTML or console logs is performed before the data is presented to the agent.
Audit Metadata