orca-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes examples and command forms that embed plaintext secrets verbatim (e.g., orca fill --element @e2 --value "s3cret", cookie set --value ), which would require the LLM to output secret values directly.

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

• Third-party content exposure detected (high risk: 0.90). The skill's Browser Automation workflow (e.g., "orca goto --url ", the example "orca goto --url https://example.com --json", plus "orca snapshot", "orca exec --command 'get html @e1'") explicitly navigates to and ingests arbitrary web pages and their DOM/content, so the agent will read and act on untrusted third‑party page content.