Memory Self-Heal
PassAudited by VirusTotal on May 11, 2026.
Overview
Type: OpenClaw Skill Name: memory-self-heal Version: 1.1.0 The skill bundle provides instructions for an AI agent to perform self-healing and diagnostic tasks. It instructs the agent to scan local directories like `memory/` and `tasks/` for error patterns using shell commands (`Get-ChildItem`/`rg` and `Select-String`). These operations are read-only and confined to expected diagnostic paths. Crucially, the `SKILL.md` includes explicit 'Safety Rules' instructing the agent to 'Never auto-run destructive operations without confirmation' and 'Never log secrets/tokens in memory files', which actively mitigate potential prompt injection risks and prevent malicious actions. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or obfuscation.
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.
The agent may take limited corrective actions without asking each time, which can save effort but should still be watched for high-impact tasks.
The skill allows the agent to retry actions and change fallback paths during a task, but it also sets a retry limit and requires validation.
Apply best-known fix from memory for same class/signature - Re-run the smallest validating action ... - Max 3 retries per blocker signature per task
Use this skill where bounded retries are acceptable, and require explicit confirmation before any destructive, account-changing, or production-impacting action.
Past logs or memory entries may affect the agent's future troubleshooting decisions, and sensitive data in those files could be brought into the agent's context.
The skill reads prior memory/tasks/logs and writes persistent self-heal entries, so stale, sensitive, or poisoned context could influence future runs.
Scan these in order; skip missing paths silently: 1. `memory/` ... 2. `tasks/` or queue files 3. runtime logs / channel logs ... Append one concise entry after each self-heal cycle
Keep memory and logs free of secrets, review self-heal writebacks periodically, and avoid treating untrusted memory/log content as authoritative instructions.