security-headers

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs scanning arbitrary public URLs and external services (e.g., usage examples like "@security-headers https://example.com", curl commands to check any site, and calls to Mozilla Observatory and securityheaders.com), so the agent would fetch and interpret untrusted third-party web content as part of its workflow.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (medium risk: 0.60). The skill includes explicit instructions and example configurations for modifying server infrastructure (e.g., Nginx/Apache config, adding headers at the webserver/load‑balancer level) which normally require editing system files and reloading system services (i.e., privileged changes that alter the machine's state), so it encourages actions that can modify the host environment even though it does not explicitly instruct privilege escalation or user creation.