react-debugging

Pass

Audited by Gen Agent Trust Hub on May 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill utilizes the ironbee-browser-devtools-cli tool, which is a resource provided by the author (ironbee-ai), to inspect React component hierarchies and properties.
  • [EXTERNAL_DOWNLOADS]: The documentation contains a link to the official React Developer Tools extension on the Chrome Web Store, which is a well-known and trusted service for development tools.
  • [PROMPT_INJECTION]: The skill presents a potential surface for indirect prompt injection as it processes untrusted data from external web applications (component props, state, and DOM structure).
  • Ingestion points: Untrusted data enters the agent context through the output of the ironbee-browser-devtools-cli tool as described in SKILL.md.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded content are present in the skill prompts.
  • Capability inventory: The skill uses Bash to execute ironbee-browser-devtools-cli for navigating pages and inspecting web content.
  • Sanitization: There is no evidence of sanitization or filtering of the data retrieved from the web pages before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 29, 2026, 01:38 AM
Security Audit — agent-trust-hub — react-debugging