agent-task-tracker

Proactive task state management. Use on EVERY task start, progress update, completion, or failure. Tracks what was requested, what's running (background proc...

This skill appears to be what it says (a small persistent task-state tracker) but there are a few things to check before installing: 1) Provenance: the included _meta.json ownerId/version differ from the registry metadata—verify the publisher and source. 2) Invocation: the doc says it should 'trigger automatically' but the registry metadata doesn't force always-on; decide whether you want automatic triggering. 3) Privacy: it records session IDs, PIDs, server names and full commands — avoid storing commands or arguments that contain secrets, and confirm the memory/tasks.md location is access-controlled. 4) Redaction: ask for or add a rule to redact sensitive fields before writing (tokens, passwords, private keys, secret-bearing args). 5) Minimality: consider making it user-invoked or limiting fields recorded to reduce leakage. If you cannot verify the owner or you are uncomfortable with persistent recording of process/host/command details, do not install or only enable it in a constrained/testing environment.

Type: OpenClaw Skill Name: new-agent-task-tracker Version: 1.0.0 The skill is designed for proactive task state management, storing operational details in `memory/tasks.md`. It instructs the agent to record its own task status, background processes (including session ID, PID, server, and command), and progress updates. While recording commands could log sensitive information if the agent were compromised by another vector, this is a functional requirement for task tracking and not indicative of malicious intent by the skill itself. There are no instructions for data exfiltration, unauthorized network calls, persistence, or other harmful actions. The instructions are clear, focused on the stated purpose, and lack any prompt injection attempts to subvert the agent for malicious ends.