Back to skill
v1.0.0

Memory Optimizer

ReviewClawScan verdict for this skill. Analyzed May 1, 2026, 7:44 AM.

Analysis

This is mostly a memory-indexing tool, but it should be reviewed because it persists full memory chunks and can keep old edited-out memory content in the index.

GuidanceReview this before installing if your OpenClaw memory contains sensitive information. If you use it, treat ~/.openclaw/workspace/memory/.index.json as sensitive, rebuild or delete the index after significant memory edits, verify the missing archive script before relying on 90-day retention, and consider pinning the watchdog dependency.

Findings (4)

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.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Rogue Agents
SeverityLowConfidenceHighStatusNote
quickstart.sh
python3 scripts/memory-watcher.py ./memory/ &

The quickstart script starts the watcher as a background process. This is disclosed and purpose-aligned, but it means the tool keeps monitoring memory files until stopped.

User impactThe tool can continue reading and indexing memory file changes after the initial command finishes.
RecommendationRun the watcher only when intended, document the stop command clearly, and consider using explicit service/PID management instead of a bare background process.
Agentic Supply Chain Vulnerabilities
SeverityLowConfidenceHighStatusNote
install.sh
pip3 install watchdog

The installer fetches an unpinned Python dependency. Watchdog is expected for file monitoring, but the exact package version and integrity are not fixed by the artifacts.

User impactInstallation depends on whatever version the package resolver retrieves at install time.
RecommendationPin the watchdog version, preferably with hashes or a lockfile, and document the package source.
Agentic Supply Chain Vulnerabilities
SeverityLowConfidenceHighStatusNote
SKILL.md
| **memory-archive** | `bash scripts/memory-archive.sh` | 季度归档 |

The skill documents an archive script as a core feature, but the supplied file manifest does not include scripts/memory-archive.sh. That makes the advertised archiving workflow incomplete in the reviewed artifacts.

User impactUsers may rely on 90-day automatic archiving or add a cron job for a script that is not actually included.
RecommendationInclude the archive script in the package or remove the archive instructions and retention claims until the implementation is present.
Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Memory and Context Poisoning
SeverityMediumConfidenceHighStatusConcern
scripts/memory-watcher.py
INDEX_FILE = Path.home() / ".openclaw" / "workspace" / "memory" / ".index.json" ... self.index["chunks"][chunk_hash] = {"content": chunk, "source": file_path, ...} ... new_chunks = self.indexer.index_file(file_path)

The watcher persists full memory chunks into a workspace index. On modification it calls index_file, whose visible logic adds chunks and updates the file record but does not clear existing chunks for the same source first, so old versions of edited memory can remain in the persistent index.

User impactInformation a user removed or corrected in a memory file may still appear in search results or be reused by an agent from the index.
RecommendationBefore re-indexing a changed file, remove all prior chunks for that file or store per-file chunk membership; provide a clear rebuild/delete-index workflow and protect the index like sensitive memory data.