Active Maintenance
PendingStatic analysis audit pending.
Overview
No static analysis result has been recorded yet. Pattern checks will appear here once the artifact has been analyzed.
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.
Installing or invoking the skill could lead the agent to run local code whose actual cleanup and memory behavior was not reviewed.
The skill instructs running a local optimizer script, but the provided manifest contains only SKILL.md and no code files, so the referenced maintenance code is outside the reviewed artifact set.
python3 /root/.openclaw/workspace/scripts/nightly_optimizer.py
Do not run the optimizer until you inspect the referenced script, confirm its source, and ensure it is the intended file.
A misconfigured or overly broad cleanup could delete files the user still needs.
The skill explicitly performs deletion, but the artifacts do not show which directories are cleaned, what is excluded, whether there is a dry run, or whether user approval is required before removal.
**Auto-Cleanup**: Remove aged temporary files and artifacts.
Require explicit user approval for deletion, review TEMP_DIRS and age thresholds, add exclusions, and prefer a dry-run report before cleanup.
Important context could be lost, altered, or over-trusted in future agent sessions.
The skill changes persistent memory content by deduplicating and summarizing it, but it does not specify scope, review, rollback, or how summaries should be trusted in later tasks.
Memory Metabolism (M3): Exact deduplication of memory fragments; Resource distillation: Summarizing dense notes into core insights.
Only run memory compaction on a reviewed memory subset, keep backups, and require review before replacing or reusing summarized memory.