chrome-devtools

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The skill's instructions are consistent with its stated purpose of browser automation and performance analysis.
  • [COMMAND_EXECUTION]: The skill describes the use of the evaluate_script tool, which allows for executing JavaScript within the context of a web page. This is a standard and expected feature for a browser automation skill.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it processes untrusted data from web pages that could contain instructions.
  • Ingestion points: take_snapshot, list_console_messages, and list_network_requests (SKILL.md).
  • Boundary markers: Absent; the skill does not provide instructions to delimit or ignore instructions found within captured page content.
  • Capability inventory: click, fill, upload_file, and evaluate_script (SKILL.md).
  • Sanitization: Absent; there are no steps described to validate or sanitize data retrieved from the browser before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 06:52 AM
Security Audit — agent-trust-hub — chrome-devtools