ClawHub
Back to skill

Security audit

Feishu Toolkit

Security checks for vulnerabilities and agentic risk

Overview

This Feishu skill is a coherent integration, but it bundles sensitive chat, document, screenshot, permission, and scheduled-message powers with limited scoping and privacy safeguards.

Review this skill before installing. Use a dedicated Feishu app with the minimum scopes needed, protect and rotate the app secret, and require explicit confirmation before chat-history access, screenshot capture, file upload, permission changes, or scheduled reminders. Avoid enabling permission-management or screenshot features unless you specifically need them.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Credential Access

High
Category
Privilege Escalation
Confidence
78% confidence
Finding

The skill requires highly sensitive credentials (FEISHU_APP_ID and FEISHU_APP_SECRET) and describes obtaining a tenant access token, which grants broad API access depending on configured scopes. While credential use is expected for this integration, the combination of document access, messaging, file upload, permission management, and reminders means compromise or misuse of these secrets could enable substantial unauthorized access and actions.

Content

Scanner excerpt · SKILL.md (reported line 41)May include surrounding context.

  1. Set FEISHU_APP_ID and FEISHU_APP_SECRET environment variables

Authentication

All API calls use Feishu's tenant access token:

python
import requests

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill includes macOS screenshot capture and transmission instructions without a strong privacy warning, scope limitation, or explicit consent requirement immediately tied to the operation. Screenshots may capture unrelated windows, secrets, personal data, or internal documents and then transmit them externally to Feishu, creating a high-risk exfiltration path.

Content

No source excerpt is available for this finding.

Exfiltration Commands

High
Category
Prompt Injection
Confidence
90% confidence
Finding

The cron template enables automated recurring outbound messages to Feishu via a system event, creating a durable exfiltration or spam mechanism if misused. Because it can persist beyond the initiating conversation and send arbitrary reminder content on a schedule, it increases the blast radius of mistaken or malicious requests.

Content

Scanner excerpt · SKILL.md (reported line 222)May include surrounding context.

--name "<task_name>"
--every ""
--session main
--system-event "[CRON] <task_name>. Send message to Feishu: '<reminder_content>'"

text

### Interval Examples

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list is broad and includes generic terms like "feishu", "lark", and common Chinese phrases, which can cause the skill to activate in contexts where the user did not intend to invoke document, chat, file, or permission operations. Because this skill can read chat history, manage permissions, send files, and create reminders, unintended activation increases the chance of privacy-impacting or state-changing actions.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 46)May include surrounding context.

md
import requests

def get_tenant_token(app_id, app_secret):
    r = requests.post(
        'https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal',
        json={'app_id': app_id, 'app_secret': app_secret}
    )

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 46)May include surrounding context.

md
import requests

def get_tenant_token(app_id, app_secret):
    r = requests.post(
        'https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal',
        json={'app_id': app_id, 'app_secret': app_secret}
    )

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The chat history feature enables retrieval and summarization of group messages without an explicit privacy warning, authorization check, or user-confirmation requirement tied to accessing potentially sensitive conversations. Summarization can condense and expose private or confidential discussion content to unauthorized requesters or broader audiences.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.