v1.0.0

公众号内容聚合

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 8:20 AM.

Analysis

This instruction-only skill is coherent for aggregating public WeChat-account content, with noteworthy but disclosed use of memory, daily pushes, and optional Feishu saving.

GuidanceBefore installing, decide whether you are comfortable with saved keyword preferences, daily 10:00 pushes, and optional Feishu record creation. If you connect Feishu, use a narrowly scoped table or workspace permission and confirm each save target.

Findings (3)

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

SKILL.md

定时推送（每天10点）

The skill describes recurring daily behavior, which is persistent/autonomous but consistent with its stated purpose.

User impactThe agent may keep producing daily content digests once configured.

RecommendationMake sure you want recurring pushes enabled and know how to pause, modify, or stop the schedule.

Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse

SeverityLowConfidenceHighStatusNote

SKILL.md

你确认后 → 存到飞书"公众号内容聚合库"

The skill can create records in a Feishu Bitable after confirmation, which requires delegated access to a third-party workspace or table.

User impactIf connected to Feishu, the agent may add records to your chosen Feishu content library.

RecommendationConfirm the exact Feishu workspace/table before saving and grant only the minimum permissions needed to create records there.

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

记录用户偏好到记忆

The skill explicitly stores user keyword preferences in persistent memory for later use.

User impactYour topic preferences may be reused in future recommendations or daily pushes.

RecommendationOnly store preferences you are comfortable keeping, and periodically review or delete saved preferences if they become outdated.