agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the agent to ask the user for a full localStorage auth token and then embed that token verbatim into an eval command (localStorage.setItem...), requiring the LLM to handle and output secret values directly.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The README includes explicit instructions to collect and inject user auth tokens and exposes arbitrary JS eval and auth-state persistence features that can be used to steal credentials and hijack sessions, representing a high risk for credential theft and unauthorized access.