deploying-laravel-cloud

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.85). The content contains deliberate patterns that enable remote code execution and potential data exfiltration (running arbitrary PHP/shell commands, fetching full --json payloads with sensitive resources) and explicitly recommends delegating verbose, sensitive outputs to subagents where the full output is hidden — behavior indicative of covert data access/exfiltration risk.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs fetching https://cloud.laravel.com/docs/llms.txt at runtime via WebFetch and to use that remote content to craft agent responses, meaning external content directly controls prompts.