agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes explicit examples of entering plaintext credentials (e.g., agent-browser fill @e2 "password123"), which instructs the agent to emit secret values verbatim in commands.

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text from a runtime-fetched web page is ingested into the agent’s LLM context via agent-browser snapshot / agent-browser get text body (page accessibility tree/body text becomes readable prose for the model).