ClawHub
Back to skill

Security audit

Feishu File Delivery

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently helps attach locally generated files to Feishu replies, but users should remember that listed files will be uploaded to Feishu.

Install this only if you want generated files uploaded into Feishu chats. Before sending a final reply, verify each absolute path points to the intended output file and does not reveal or attach unrelated local content.

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

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README instructs users to place absolute local file paths in Feishu replies so the adapter will automatically upload those files as attachments, but it does not clearly warn that this causes data to leave the local environment and be transmitted to a third-party chat platform. In a skill specifically designed to move locally generated documents into Feishu, this omission increases the risk of accidental disclosure of sensitive files, especially if users misunderstand which paths will be uploaded or reuse the pattern in broader workflows.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly instructs agents to include absolute local file paths in Feishu replies so an adapter can automatically upload matching files. This creates a real data-exposure risk because local paths may reveal host filesystem structure and, if the produced path is wrong or attacker-influenced, the workflow could cause unintended local files to be shared without an explicit user confirmation step.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to trigger automatic upload of a local file to Feishu immediately after composing a caption and appending the absolute path, without any explicit user confirmation, destination verification, or warning that data will leave the local environment. This creates a real risk of unintended exfiltration of sensitive files, especially because the skill is designed to handle locally generated documents and normalizes automatic transmission as part of routine behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly promotes automatic upload of locally generated files to Feishu but does not disclose that local content will be transmitted to an external chat platform or warn about privacy implications. This creates a real risk of unintended data exfiltration, especially if generated files contain sensitive business data, personal information, or intermediate artifacts that users may not expect to leave the local/runtime environment.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill presents operational instructions in Chinese alongside English, which imposes a language/locale assumption on users without stating that bilingual output is optional or required for a specific audience. Under the policy, language constraints should be user-selectable or explicitly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.