proxelar

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

• Third-party content exposure detected (medium risk: 0.30). The skill acts as a proxy intercepting HTTP traffic, allowing an outsider making requests through the proxy to supply free text in request headers or bodies that the agent or logging scripts ingest.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill documentation includes a command using sudo to install a trusted CA certificate into the system keychain, which represents a security modification.