Agkan
PassAudited by VirusTotal on May 11, 2026.
Overview
Type: OpenClaw Skill Name: agkan Version: 0.1.0 The agkan skill bundle provides a standard interface for an AI agent to interact with a local SQLite-based task management CLI tool. The documentation in SKILL.md defines typical kanban operations such as task creation, status updates, tagging, and dependency management without any signs of malicious intent, data exfiltration, or unauthorized execution.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
An agent using the skill could update, re-tag, or delete tasks if the user asks it to manage the board.
The skill documents commands that can mutate or delete task-board records. This is aligned with the stated task-management purpose, but it can still affect project data if used on the wrong task ID.
agkan task update <id> --status in_progress ... agkan task delete <id>
Review task IDs and intended changes before destructive actions such as delete operations.
The skill itself does not add code, but its behavior depends on whichever agkan executable is present in the user's environment.
The skill relies on the external agkan CLI, but the artifact does not install, pin, or declare that binary. Users must supply and trust the local CLI themselves.
No install spec — this is an instruction-only skill.
Install agkan only from a trusted source and confirm the expected binary is on PATH before relying on this skill.
Incorrect or untrusted task metadata could influence future task selection or project workflow decisions.
The task database and metadata are persistent and may influence later agent workflows. This is expected for a task-management system, but users should be aware that stored task content can be reused later.
`agkan` is an SQLite-based CLI task management tool... Skills that select tasks for execution (e.g., `agkan-run`) read this value to determine which task to work on next.
Avoid storing secrets or untrusted instructions in task bodies or metadata, and review priorities/metadata before automated task selection.