setup-transcriptformer-remote-tool

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

• Third-party content exposure detected (low risk: 0.10). The runtime workflow shown in SKILL.md starts a local MCP server (http://127.0.0.1:7000/mcp) and forwards only tool calls/arguments from the user-supplied invocation context; it does not describe any mechanism where outsider-authored free text from external feeds (e.g., email/chat/issue text) is ingested without first selecting a specific item.

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

• Potentially malicious external URL detected (high risk: 1.00). The setup instructs pip to install a remote wheel at https://connect.aiscientist.tools/downloads/tuplatform_connect-0.3.0-py3-none-any.whl#sha256=3fad5eee5ecf7887a693d93ccd1aa112dc0955617a885d1fc3daded0030f9ae0 during runtime, which fetches and installs remote code that the skill relies on.