agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt contains explicit examples that embed credentials verbatim into commands (e.g., agent-browser fill @e2 "password123" and use of "$USERNAME"/"$PASSWORD"), so an LLM following these patterns may be required to output secret values directly.

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

• Third-party content exposure detected (high risk: 1.00). The skill's core workflow and examples (SKILL.md) and templates (e.g., templates/capture-workflow.sh) explicitly navigate to arbitrary URLs via "agent-browser open " and extract page content with commands like "agent-browser snapshot -i" and "agent-browser get text body", meaning the agent fetches and interprets untrusted public web content that can influence subsequent actions.