Feishu Bitable Query

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:14 PM UTC
• Version:
  1.0.0

Overview

This is a documented Feishu table-query helper that uses existing Feishu credentials to read records, with no hidden persistence, mutation, or unrelated behavior found.

Install only if you intend this skill to use the Feishu app credentials already stored in ~/.openclaw/openclaw.json. Use least-privilege Feishu app permissions, verify each app-token and table-id before running queries, and avoid --all-pages or broad filters unless a full table export is actually needed.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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

Findings (2)

Vague Triggers

Medium

• Confidence: 79% confidence
• Finding: The activation guidance is broad enough that an agent could invoke the skill in many Feishu-related querying situations without clear user intent boundaries. In combination with automatic credential use and network access, ambiguous triggers increase the chance of unnecessary or overbroad access to enterprise table data.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill states that it automatically reads Feishu credentials from a local secrets file, but does not provide a user-facing warning or consent checkpoint. This is dangerous because an agent can silently leverage stored enterprise credentials to query potentially sensitive Bitable data, increasing the risk of unauthorized access, data leakage, and misuse of ambient credentials.

VirusTotal

66/66 vendors flagged this skill as clean.