daily-report-bian

• Outcome: Pass
• Latest audit: May 29, 2026, 8:19 PM
• Version:
  1.0.2

Overview

This daily-report skill handles sensitive chat and memory data, but its behavior is disclosed and matches its stated reporting purpose.

Install only if you are comfortable with Feishu/OpenClaw chat content and recent memory notes being summarized, saved back into daily memory, and potentially delivered through Feishu on a schedule. Review the cron job, recipient, schedule, and memory retention expectations before enabling it.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (6)

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The skill description states that it reads same-day conversation JSONL records and the last 7 days of memory files, but it does not prominently warn the user that potentially sensitive conversational and memory data will be accessed for report generation. This creates a privacy and consent risk because users may enable or invoke the skill without realizing the scope of data collection and downstream summarization.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill documents automatic scheduled delivery via Feishu private chat, but it does not clearly warn users that generated reports may be pushed automatically on a timer without per-send confirmation. That is dangerous because summaries derived from chats and memory files could disclose sensitive information to the wrong recipient, at the wrong time, or in an unexpected context.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The script automatically reads the latest Feishu session history and extracts today's messages without any user-facing consent, warning, or scope restriction. Conversation logs commonly contain sensitive data, and silently ingesting them into a reporting workflow increases the chance of privacy violations and unintended disclosure in derived outputs.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The script appends generated report content into a persistent daily memory file automatically, modifying user data without an explicit warning or confirmation. This can permanently store sensitive or incorrect summaries, expanding the exposure window and making later unintended reuse more likely.

Ssd 3

Medium

• Confidence: 94% confidence
• Finding: The documented workflow aggregates session contents and memory entries into a plain-language report and stores it back into persistent memory, which creates a data-retention and leakage path by design. Summaries can surface sensitive details in a more readable form, making accidental disclosure to later tools, users, or automations more likely.

Ssd 3

Medium

• Confidence: 96% confidence
• Finding: The code explicitly reads today's messages from session logs and feeds them into report generation that is later persisted, effectively converting ephemeral conversation data into retained memory. In this skill context, that behavior is more dangerous because the source includes direct chat history, which may contain confidential operational, personal, or business information not intended for long-term storage.

VirusTotal

50/50 vendors flagged this skill as clean.