v1.0.0

Daily Memory Keeper

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 8:15 AM.

Analysis

This instruction-only skill is coherently focused on organizing AI memory files, but users should notice that it creates persistent cross-session memory and can automatically clean old memory files.

GuidanceBefore installing, make sure you are comfortable with the skill creating a persistent memory archive under the configured directory and automatically deleting entries older than the retention period. Set the directory and retention days deliberately, avoid storing secrets in memory, and review important retrieved memories before acting on them.

Findings (2)

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.

Cascading Failures

SeverityLowConfidenceHighStatusNote

SKILL.md

"retentionDays": 30, "autoClean": true

The default configuration includes automatic cleanup of retained memory data after a set period.

User impactIf retention is set too short or the wrong archive directory is used, useful memory history could be deleted and affect future sessions.

RecommendationConfirm the archive directory and retention period before use, and keep backups if the memory history is important.

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

SeverityLowConfidenceHighStatusNote

SKILL.md

按日期归档成知识库，支持快速检索和跨会话记忆

The skill intentionally persists agent memory into a reusable knowledge base and makes it available across sessions.

User impactOld, sensitive, or incorrect memory could be reused in later sessions if the archive is not reviewed or managed.

RecommendationUse a dedicated memory directory, avoid storing secrets in agent memory, and review retrieved memories before relying on them for important actions.