T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:143- Finding
Automatic External Transmission Without User Authorization
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md, lines 143–149
Vulnerability Type: Automatic transmission of generated files to an external messaging service
Risk Level: HighVulnerable code:
text ### Step 2: 发送飞书 使用 message tool 发送 PDF:javascript message({ action: "send", message: "📊 [主题]框架法终局推导", filePath: "research/[topic]-analysis-[date].pdf" })Technical Analysis
The Skill instructs the agent to transmit every generated report through the Feishu messaging integration automatically. It does not require explicit user consent, display or validate the destination, classify the report's sensitivity, or provide a local-only delivery option.
Because the report is derived from user input and external research, it may contain confidential topics, sensitive assessments, personal information, or other material that the user did not intend to disclose outside the current environment. The instruction crosses a trust boundary from local analysis and file generation to an external service without an authorization checkpoint.
Attack Path
- A user requests a framework analysis and supplies a potentially sensitive subject or supporting information.
- The Skill incorporates the supplied information and research results into a Markdown report.
- The report is converted into a PDF.
- The Skill automatically invokes the
messagetool with the generated PDF. - The PDF is uploaded to the Feishu destination associated with the active tool context without confirming the recipient or obtaining the user's approval.
- Anyone with access to that destination may obtain the report and its sensitive contents.
Impact Assessment
Exploitation does not grant new operating-system privileges, but it abuses an already authorized messaging capability beyond the minimum permissions needed to perform local analysis. The exposed scope can include the entire generated report, user-supplied info ...[truncated 290 chars]
- Remediation
View remediation
Remediation Suggestions
- Remove automatic external delivery and make local report generation the default behavior.
- Require explicit, per-transmission user confirmation after the report has been generated.
- Before confirmation, display the exact file path, destination service, channel or recipient, and a concise description of the data being sent.
- Validate the destination against an approved allowlist rather than relying on ambient messaging context.
- Add a sensitivity review that detects credentials, personal information, confidential input, and restricted material before upload.
- Apply least privilege to the messaging integration and prevent the Skill from choosing arbitrary recipients.
- Record an audit event for each approved transmission without logging the report's sensitive contents.
- Provide a local-only or manual-download alternative when authorization is absent.
