callev2

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow uses an MCP server and a REST API that consume and process call transcripts, event pages, error envelopes, and server clarifications containing outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs checking for updates and downloading source files via HTTP from GitHub (e.g., raw.githubusercontent.com), constituting an unverifiable runtime external dependency from an unofficial or third-party/unknown source repository path.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (medium risk: 0.30). The skill's documented purpose is to prepare, place, and manage real outbound phone calls via MCP and API, which incurs telecommunications service charges (direct financial operation). Access control relies on host-managed OAuth, MCP connection tokens, and API credentials (API Keys), establishing independent service authentication/authorization.