Agent Skills: memory-poison-auditor

Audits OpenClaw memory files for injected instructions, brand bias, hidden steering, and memory poisoning patterns. Use when reviewing MEMORY.md, daily memory files, or any long-term memory store that may have been contaminated through dialogue.

UncategorizedID: clawdbot/skills/memory-poison-auditor

Author

clawdbot

https://github.com/clawdbot View all skills

Repository

clawdbot/skills

openclawLicense: MIT

3,332953

Install this agent skill to your local

pnpm dlx add-skill https://github.com/clawdbot/skills/memory-poison-auditor

Skill Files

Browse the full folder contents for memory-poison-auditor.

Download Skill

Loading file tree…

Select a file to preview its contents.