Back to skill

Security audit

Yq Feishu Webhook Skill

Security checks for vulnerabilities and agentic risk

Overview

This Feishu webhook skill is mostly purpose-built, but it needs Review because it can post user content externally and documents a risky way to pass a tenant token on the command line.

Install only if you intend agents to send selected content to Feishu/Lark. Prefer FEISHU_TENANT_ACCESS_TOKEN from a protected secret store, avoid the documented --token argument, verify the webhook URL and exact message content before sending, and do not upload sensitive images or secrets unless they are meant to be shared in that Feishu destination.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/upload_image.py:78
Finding

Tenant Access Token Exposure Through Command-Line Arguments

Content
View full analysis
--token ``` ### Technical Analysis The uploader accepts a Feishu tenant access token through the `--token` command-line option. Command-line arguments are commonly exposed to other local users through process-inspection facilities while the process is running. They may also be retained in shell history, terminal session recordings, CI/CD job output, audit telemetry, or process-monitoring systems. Although the script also supports the safer `FEISHU_TENANT_ACCESS_TOKEN` environment variable, the command-line alternative remains enabled and is explicitly documented. The token is legitimately required to authenticate the image upload to the fixed official Feishu HTTPS endpoint, but exposing it through process arguments is not necessary for that functionality. No evidence indicates that the script sends the token to an unrelated destination. The network operation itself is expected for image upload; the vulnerability concerns local disclosure caused by the credential input mechanism. ### Attack Path 1. A user follows the documented example and invokes the uploader with `--token`. 2. The tenant access token becomes part of the process command line. 3. The command may be stored in shell history or captured by job logs, process monitoring, terminal recording, or loc ...[truncated 960 chars]
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)

Tainted flow: 'headers' from os.environ.get (line 65, credential/environment) → requests.post (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/upload_image.py (reported line 69)May include surrounding context.

python
"Authorization": f"Bearer {token}",
            "Content-Type": form.content_type,
        }
        response = requests.post(url, headers=headers, data=form, timeout=30)

    result = response.json()
    return result

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list is unusually broad and includes generic terms such as '消息', '通知', and brand names like 'Feishu'/'Lark', making accidental invocation likely during ordinary conversation. Because this skill sends data to an external webhook, overbroad activation increases the chance that user content is routed off-platform without clear intent or confirmation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill is designed to transmit message content to a third-party Feishu webhook, but it does not prominently warn that user-provided data will leave the current system and be sent to an external service. In combination with broad triggers, this omission raises the risk of unintended disclosure of sensitive or confidential information.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

该 markdown 文件的全部说明、标题和示例描述均以中文呈现,没有提供可选语言、国际化说明或明确的区域适用范围。按照语言/locale 政策,若技能内容实际上强制特定语言而未给用户提供选择或合理说明,可构成自然语言策略违规。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The document title and introductory text are entirely in Chinese, with no indication that other languages are available or that the locale is intentionally restricted. Under the stated policy, natural-language content that forces a specific language without user opt-in can be a locale-policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file presents all instructions and examples exclusively in Chinese, which effectively forces a specific language for users consuming the skill documentation. The policy for natural-language violations calls for flagging language or locale constraints when no user opt-in or alternative is offered.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

该 Markdown 文档通篇以中文编写,未见提供多语言版本、语言选择机制,或声明该文档仅面向中文用户/特定区域使用。根据规则,强制单一语言而无用户选择或明确合理说明,属于自然语言层面的语言/locale 策略风险。

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file documents a network operation that sends image content to a remote service, which can affect user privacy or data handling. While it explains authentication and request details, it does not include any explicit user-facing warning that the image will be uploaded to Feishu's servers.

Content

No source excerpt is available for this finding.