Agent Browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt contains commands and examples that embed credentials and passwords directly (e.g., fill @e2 "password123", agent-browser set credentials user pass, cookies set name value), so an LLM generating those commands would need to include secret values verbatim in its output.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow includes agent-browser open <url> and snapshot which fetches and parses arbitrary web page DOM/accessibility text from the provided URL, so outsider-authored free text from public web content is ingested into the agent’s LLM context via the snapshot output.