agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt's CLI examples show entering plaintext credentials (e.g., agent-browser fill @e2 "password123") and instruct filling forms with variables that would be substituted into commands, which forces the agent to emit secret values verbatim into generated commands/outputs.

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs the agent to "open " and to use commands like snapshot -i, get text, and snapshot --json to fetch and read arbitrary public web pages (e.g., "agent-browser open https://example.com/products"), meaning it will ingest untrusted third-party site content that can influence subsequent interactions.