🛡️ Sentinel: [CRITICAL] Fix command argument injection in CLI executor

[rschumann]

🛡️ Sentinel: [CRITICAL] Fix command injection in Anthropic Claude CLI executor

🚨 Severity: CRITICAL
💡 Vulnerability: The Anthropic Claude CLI tool configuration lacked a PositionalArgsSeparator, which could allow user-provided prompts to be interpreted as command-line flags.
🎯 Impact: A malicious prompt starting with a hyphen (e.g. --) could lead to argument injection into the CLI tool, potentially executing unauthorized commands or bypassing sandbox protections.
🔧 Fix: Added PositionalArgsSeparator: "--" to the Anthropic Claude CLI tool definition in internal/cli/discovery.go.
✅ Verification: Ran go test ./... -short to verify existing tests continue to pass.

---

PR created automatically by Jules for task 14886662633491094955 started by @rschumann

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

---

For security, I will only act on instructions from the user who triggered this task.