Back to skill

Security audit

feishuweng

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims: it sends user-provided text messages through Feishu using configured Feishu app credentials.

Install this only if you intend the agent to send Feishu messages with the configured app credentials. Treat message text and recipient IDs as data shared with Feishu, and avoid sending secrets or regulated information unless that is approved for your workspace.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill documentation does not warn that user-supplied message text and recipient identifiers are transmitted to the external Feishu API. This can cause users or calling agents to send sensitive data off-platform without informed consent, increasing privacy, compliance, and data-handling risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This code performs outbound HTTP requests to Feishu, including transmitting app credentials to obtain a tenant token and sending user-provided message text to the messaging API. There is no confirmation prompt, logging, or explanatory comment disclosing these network and data-transmission behaviors to the user.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% 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 · main.py (reported line 12)May include surrounding context.

python
def get_tenant_token(self):
        url = "https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal"
        resp = requests.post(url, json={
            "app_id": self.app_id,
            "app_secret": self.app_secret
        })

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% 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 · main.py (reported line 27)May include surrounding context.

python
"msg_type": "text",
            "content": f'{{"text":"{text}"}}'
        }
        return requests.post(url, headers=headers, json=data).json()

# OpenClaw 固定入口
def run(config, params):

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The entire skill documentation is written in Chinese and presents the skill as a general-purpose capability, with no indication that language is optional or that the locale restriction is intentional and justified. The policy requires avoiding forced language or locale constraints unless the user can opt in or the limitation is clearly documented.

Content

No source excerpt is available for this finding.