Back to skill

Security audit

飞书多维表格 AI 管家

Security checks for vulnerabilities and agentic risk

Overview

This Feishu Bitable helper can read and modify tables, but that access is disclosed, purpose-aligned, and not paired with hidden code or persistence.

Install only if you intend the agent to operate on Feishu Bitable data. Before bulk updates or inserts, confirm the target base, table, fields, and records, especially for customer or employee information.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger phrases are broad enough to match generic spreadsheet or data-processing requests, which can cause the wrong skill to activate. In this skill’s context, mistaken activation is risky because the skill is designed not only to read but also to create and update Feishu Bitable records, potentially leading to unintended data access or modification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill describes bulk record creation, updates, and report writing, but it does not clearly warn that using the skill may modify user data. Without an explicit write-capability warning, users or orchestrating agents may invoke it assuming it is read-only, increasing the chance of unintended changes to production tables.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file includes workflows that retrieve and process customer contact data and employee records, including phone numbers, names, departments, and employment details. Under SQP-2 for markdown files, descriptions that affect user data or privacy should include warnings, but these examples present bulk access and modification steps with no disclosure about sensitivity, privacy impact, or review before execution.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This scenario instructs the AI to batch-update departments and add employee records, which can directly affect organizational data integrity. The markdown does not warn users that these actions modify records in bulk or recommend verification before applying changes, which fits the missing-warning criterion for markdown files.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

All headings, instructions, and example prompts are written in Chinese, including direct user utterances, with no indication that other languages are supported or that the Chinese-only format is intentional for a region-specific tool. Per SQP-3, forcing a specific language without user opt-in can be a natural-language policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file contains user-facing instructional content only in Chinese, including the title and all field descriptions. Under the policy rule for language or locale, a skill should not force a specific language unless it is clearly documented as a justified regional constraint or offers user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.