Prompt Library Gardener

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: prompt-library-gardener Version: 1.0.1 The 'Prompt Library Gardener' skill is a purely instruction-based (prompt-flow) tool designed to help users organize and index their prompt collections. It contains no executable code, requires no network or API access, and includes explicit safety boundaries in SKILL.md and ACCEPTANCE.md that forbid the agent from searching local files, browser history, or external accounts. The logic is entirely focused on text processing and organization within the chat context.

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.

What this means

Prompts pasted into the chat may be summarized and reused in the generated index, so private instructions, secrets, or unsafe prompt variants could be exposed within the conversation output if the user includes them.

Why it was flagged

The skill intentionally processes and summarizes user-provided prompt text in the conversation. This is purpose-aligned and bounded, but prompt libraries can contain sensitive or instruction-like content.

Skill content
Keep sensitive prompt content private within the current conversation. ... Keep a running index only from batches already provided.
Recommendation

Paste only prompt content you are comfortable sharing in the chat, redact secrets, and treat saved prompt text as data to organize rather than instructions for the agent to follow.