speakai@1.42.1
VERIFIED· install onlyPublisher claims: "Connect an agent to Speak AI and orient it in the workspace. Covers the remote OAuth connection, the local stdio connection with an API key, the MCP tools and their categories, the resources, the built-in prompts, and the first workflows to run. Use this when you need to set up the Speak AI MCP server, when a Speak AI tool is missing or returning 401, or when you need to know which tool to call to transcribe a recording, read a transcript or captions, search across a media library, ask questions about recordings, create clips, export transcripts, run voice and video surveys with recorders, schedule the meeting assistant for Zoom, Google Meet or Microsoft Teams, or manage folders, custom fields, webhooks, automations, dashboards and team members." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-13 and scored it 93/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
…ers, actions, runs, and app catalog. Available only on the local stdio server (`npx @speakai/mcp-server`); on the hosted server, set up automations in the Speak AI web app | `list_automa…Fix: Pin versions and sources; vendor anything fetched at install time.- **ChatGPT:** Settings, then Apps and Connectors, then Advanced, then turn on developerFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.… and prompt tools. AI Chat itself is available only on the local stdio server (`npx @speakai/mcp-server`) | `get_chat_history`, `list_prompts`, `export_chat_answer` | | `search-analytic…Fix: Pin versions and sources; vendor anything fetched at install time.- **ChatGPT:** Settings, then Apps and Connectors, then Advanced, then turn on developerFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.