orca-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt contains explicit examples and commands that embed secret values verbatim (e.g., orca fill --value "s3cret", orca cookie set --value ) which encourages the agent to generate outputs containing plaintext secrets, posing exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "Browser Automation" section explicitly instructs the agent to navigate arbitrary URLs and snapshot page content (e.g., orca goto --url , orca snapshot, orca exec --command "get text @e1"), so the agent will fetch and interpret untrusted third‑party web pages and act on their contents, creating a clear path for indirect prompt injection.