agent-browser-security-production-safety

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies and attempts to mitigate the risk of indirect prompt injection by processing untrusted browser data.
  • Ingestion points: Browser page text, console output, network payloads, and downloaded files (SKILL.md, 01-auth-state-secrets-trust.md).
  • Boundary markers: Explicit instructions are present to treat all browser content as untrusted and to disregard page-provided instructions that conflict with the safety contract.
  • Capability inventory: Uses the agent-browser CLI to interact with the environment and process files.
  • Sanitization: Strictly requires the redaction and masking of PII, secrets, and authentication tokens before sharing artifacts.
  • [COMMAND_EXECUTION]: The skill incorporates the use of the agent-browser CLI tool, instructing the agent to execute commands for version checking and loading local skill guidance (SKILL.md, Step 2).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 02:31 PM
Security Audit — agent-trust-hub — agent-browser-security-production-safety