Memory Poison Auditor

INLINECODE0 checks whether OpenClaw memory files have been contaminated by hidden instructions, brand steering, injected operational policies, or suspicious recommendation bias written through prior conversations.

What It Checks

• - Prompt-injection style instructions inside memory.
• "Always recommend X" or "never mention Y" style brand steering.
• Abnormal brand repetition and preference shaping.
• Suspicious authority claims like fake approvals or fake user intent.
• Low-signal blocks that act like covert policy rather than factual memory.
• Optional AI review for borderline suspicious blocks.

Commands

Audit Default Memory Roots

CODEBLOCK0

Audit a Specific Path

CODEBLOCK1

Optional AI Review

CODEBLOCK2

One-Click Cleaning

CODEBLOCK3

Cleaning creates backups before rewriting suspicious blocks.

Output

Each audit returns:

• - PASS: no meaningful poisoning signals
• INLINECODE2: suspicious memory blocks detected
• INLINECODE3: memory likely contaminated and should be reviewed/cleaned

Reports and backups are written to:

CODEBLOCK4

Operational Guidance

• - Use this before trusting long-term memory in important planning or recommendations.
• INLINECODE4 means review before relying on that memory block.
• INLINECODE5 means clean or quarantine the memory before reuse.
• AI review is optional and intended only for ambiguous cases.