Memory Management

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This is a coherent local trading-memory skill, but it stores and curates persistent trading records, so users should review backups and any external helper scripts before relying on it.

Before installing, make sure you are comfortable with the agent maintaining local trading memory files under /Users/zst/clawd. Keep backups of MEMORY.md and the memory directory, review any automated cleanup results, and do not run the referenced Python helper scripts unless you have inspected their source.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

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.

What this means

Future trading analysis could be biased by inaccurate or low-quality stored lessons.

Why it was flagged

The skill is designed to write distilled lessons into a long-term memory file, meaning incorrect or poisoned entries could be reused in future trading-related tasks.

Skill content
提炼高价值记忆到 MEMORY.md
Recommendation

Periodically review MEMORY.md and the trading memory directory, and keep backups before allowing automated summarization or cleanup.

What this means

Useful historical trading context could be archived or cleaned incorrectly, which may influence later comparisons or decisions.

Why it was flagged

The maintenance protocol can alter or remove historical memory records. This is consistent with the skill's purpose, but unclear cleanup criteria could affect future analyses.

Skill content
每周 (周六 23:00)
- 归档旧记忆文件 (>30 天)
- 清理重复/低质量记忆
- 更新记忆系统统计
Recommendation

Require user confirmation or maintain versioned backups before cleaning or archiving trading memory files.

What this means

If the user supplies or downloads these scripts separately, their behavior and provenance would determine additional risk.

Why it was flagged

The skill references helper scripts, but the provided artifact set contains only SKILL.md and no code files, so those helpers were not available for review.

Skill content
- `memory_evaluator.py` - 记忆质量评估
- `auto_memory_manager.py` - 自动记忆管理
Recommendation

Review any external helper scripts before running them, especially scripts that automatically modify memory files.