agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes explicit examples that embed plaintext passwords and echo/pipeline commands (e.g., agent-browser fill @e2 "password123", echo "pass" | agent-browser auth save ...) which would require an LLM to produce secret values verbatim if following those examples, so it presents a high exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.95). Outsider-authored free text is ingested when the required runtime step agent-browser snapshot -i (and get text body) reads the target page’s accessibility tree/body text from the navigated URL (public web content or other third-party pages) into the agent’s LLM context.