Security audit

Feishu Requirement Manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Feishu requirements-management guide, with expected table creation and record updates, but users should be aware it stores Feishu table identifiers in shared memory.

Install only if you want an agent to manage Feishu Bitable requirement records. Before first use, confirm which Feishu app and tables it may create or modify, and decide whether storing app_token and table_id values in shared memory is acceptable for your workspace.

A.I.G

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

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger keywords are very broad and overlap with common project-management phrases such as '创建需求', '查看进度', and '添加任务'. This can cause the skill to activate unintentionally in unrelated conversations, leading to unintended table operations, task creation, or workflow execution in Feishu when the user did not explicitly intend to invoke this skill.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The example workflow explicitly persists app and table identifiers to a shared memory file and later uses them to query and modify records, but it does not show any user notice, confirmation, or consent around persistent storage and subsequent state-changing actions. In an agent setting, this can normalize silent retention of workspace metadata and silent modification of user data, increasing the risk of unintended cross-session access, privacy issues, and unauthorized changes if the shared memory is reused broadly.

Static analysis

No suspicious patterns detected.