usewhisper-autohook

Automatically fetches and injects Whisper memory context before responses and ingests conversation turns after, optimizing token usage for Telegram agents.

This skill appears to do what it says: it queries a Whisper Context service before responses and ingests turns afterwards, and it can run a local proxy to reduce token usage. Before installing or running it, consider: 1) Privacy: the script will transmit full user messages and assistant replies to the external Whisper Context API (and may auto-create the project); do not use for sensitive or regulated data unless you trust the provider and understand their retention policy. 2) Local files: it stores small state (context_hash) under your user home directory to enable delta compression — inspect the script to find the exact path if you need to manage it. 3) Proxy usage: if you run the proxy you must supply your upstream OPENAI/ANTHROPIC API key; run the proxy only on a local/private host and ensure the port is not publicly accessible. 4) Review the source: the author recommends reviewing the script before use; if you are not comfortable, don't provide API keys or run the proxy. If you want a deeper check, provide the full untruncated usewhisper-autohook.mjs for line-by-line review (I reviewed the provided excerpts).

Type: OpenClaw Skill Name: usewhisper-autohook Version: 1.0.0 The OpenClaw skill 'usewhisper-autohook' is designed for memory management by integrating with the Whisper Context API. It makes outbound HTTPS requests to `context.usewhisper.dev` and user-configured upstream LLM APIs (OpenAI/Anthropic), using API keys provided via environment variables. It persists a `context_hash` locally in `~/.openclaw/.cache/usewhisper-autohook/state.json` for delta compression, which is a benign caching mechanism. The proxy modes (`serve_openai_proxy`, `serve_anthropic_proxy`) start local HTTP servers to intercept and modify LLM API calls, injecting memory context. All observed behaviors, including network calls, local file writes, and environment variable access, are directly aligned with the stated purpose of providing automatic memory for AI agents. There is no evidence of intentional malicious activity such as unauthorized data exfiltration, arbitrary code execution, persistence mechanisms beyond caching, or deceptive prompt injection attempts in `SKILL.md`.