Cerebro Openclaw Memory Boost Kb

PassAudited by VirusTotal on May 11, 2026.

Overview

Type: OpenClaw Skill Name: cerebro-openclaw-memory-boost-kb Version: 0.1.0 The skill bundle implements a 'Cerebro-first' operational protocol designed to improve agent continuity and knowledge management through structured markdown documentation. It enforces a read-before-act workflow, domain-based task routing, and mandatory write-backs to memory logs, all of which are consistent with its stated purpose as a memory boost and knowledge base. No indicators of data exfiltration, malicious execution, or harmful prompt injection were found across the SKILL.md or reference files.

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.

NoteHigh Confidence
ASI01: Agent Goal Hijack
What this means

If Cerebro documents are stale or wrong, the agent may pause, challenge, or redirect the task instead of simply following the latest chat instruction.

Why it was flagged

The skill intentionally makes persistent Cerebro documentation more authoritative than the current chat context, which can change how the agent handles conflicting user requests.

Skill content
Priority order: **Cerebro > SOUL/AGENTS > MEMORY > chat history**.
Recommendation

Keep Cerebro documents current and review any conflict prompts before allowing the agent to update docs or proceed.

What this means

Private project notes, company context, or personal trading context may be read and reused, and incorrect write-backs could influence later sessions.

Why it was flagged

The skill relies on persistent local memory and source-of-truth files, and it instructs the agent to write updates back into those stores.

Skill content
Read continuity logs: `memory/YYYY-MM-DD.md` for today and yesterday ... Update authoritative Cerebro file ... Append to `memory/YYYY-MM-DD.md`
Recommendation

Review stored Cerebro and memory files periodically, avoid placing secrets in them, and check write-back summaries for accuracy.