TreeListy
Analysis
Prompt-injection indicators were detected in the submitted artifacts (system-prompt-override, unicode-control-chars); human review is required before treating this skill as clean.
Findings (2)
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.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
git clone https://github.com/prairie2cloud/treelisty-openclaw-skill.git ~/.openclaw/skills/treelisty ... npm install
The documented setup asks users to clone a repository and install npm dependencies for the Node CLI. This is consistent with the skill's purpose, but it is still a dependency/provenance step users should trust before running.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
const wsUrl = `ws://${host}:${port}`; ... token: token ... arguments: { tree: tree, source: 'openclaw-skill' }The optional push feature sends the tree and any supplied token to a WebSocket endpoint. It defaults to localhost and is purpose-aligned, but users should understand what data is sent.
