My Tasks

View your personal task history and status on OpenAnt. Use when the user wants to see their own tasks, check what they've completed, review their task histor...

This skill appears to do what it says: read-only queries of your OpenAnt tasks. Before installing/using it, consider: 1) npx @openant-ai/cli@latest will download and run code from npm each time — only run it if you trust the @openant-ai/cli package and its publisher; prefer a pinned version/checksum if possible. 2) The skill is written to execute commands immediately (no extra confirmation). If you want tighter control, run the CLI commands manually first to verify output and authentication. 3) Ensure the authenticate-openant skill (or whatever you use to sign in) is trustworthy, since --mine queries depend on your session token. If any of these points worry you, run the CLI locally yourself instead of allowing autonomous execution.

Type: OpenClaw Skill Name: my-tasks Version: 0.1.0 The skill is designed for read-only task management, and its instructions explicitly state this. However, the `SKILL.md` file defines `allowed-tools` with broad `Bash` execution permissions, specifically allowing `npx @openant-ai/cli@latest tasks list *` and `tasks get *`. The wildcard `*` permits the agent to append arbitrary strings to these commands. This creates a significant shell injection vulnerability, as a malicious user or a prompt injection could instruct the agent to append shell metacharacters (e.g., `; rm -rf /`) to the `npx` command, leading to unauthorized command execution. While there is no explicit malicious instruction within the skill itself, this broad permission constitutes a critical vulnerability.