agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes examples that embed secrets directly in commands/URLs (e.g., Authorization: "Bearer " in --headers and a CDP wss URL with ?token=...), which would require the agent to include secret values verbatim in its output.

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

• Third-party content exposure detected (high risk: 0.90). The skill's core workflow and commands (e.g., "agent-browser open " and "agent-browser snapshot -i" in SKILL.md) explicitly fetch and parse arbitrary public web pages and allow the agent to read, interpret, and act on that untrusted third-party content (click/fill/eval), enabling indirect prompt-injection risks.