Prompting

• Analyzed: May 12, 2026, 4:12 AM
• Findings: 1
• Version: 1.0.0
• Hash: e326270e230bdef915c99bd63fd4a105642128071c0c33e579dbb42ddfe7e8a8
• Source: palm
• External report: View on VirusTotal

Findings (1)

The skill bundle is designed to assist with prompt engineering, including managing user preferences, prompt patterns, and iteration history within the `~/prompting/` directory. It instructs the AI agent to read from and write to `~/prompting/memory.md` and `~/prompting/history.md`, which is directly aligned with its stated purpose. The `memory-template.md` file contains a `mkdir -p ~/prompting/patterns` command for directory setup, which is a benign file system operation. There is no evidence of data exfiltration, unauthorized remote execution, persistence mechanisms, or prompt injection attempts against the OpenClaw agent itself. The instructions for generating 'adversarial inputs' are for testing other AI models, not for malicious actions by the skill.