dogfood

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to request and then insert user credentials (e.g., {EMAIL}, {PASSWORD}, OTP) verbatim into agent-browser commands and fills, which requires the LLM to handle and output secrets directly.

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly opens and explores an arbitrary Target URL (e.g., "agent-browser --session {SESSION} open {TARGET_URL}" and the "Explore" steps in SKILL.md), so it fetches and interprets content from untrusted public websites as part of its testing workflow.