Back to skill

Security audit

Feishu

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Feishu workflow assistant that requests broad but purpose-aligned workplace integration and includes clear confirmation boundaries for writes.

Install only with a Feishu app whose scopes match what you actually need. Start in counselor mode for read-only summaries and drafts, and use executive mode only when you are comfortable allowing confirmed actions such as sending messages, editing tables, or coordinating schedules.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file uses Chinese throughout examples and headings, which implies a fixed language experience for the skill. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger phrases include very generic workplace requests such as meeting notes, weekly report generation, and message organization. In a broadly integrated enterprise skill, overly broad triggers can cause accidental invocation during normal conversation, leading the agent to access or act on Feishu data or workflows when the user did not clearly intend to use this skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The audience is explicitly limited to "中国企业管理者" and related Chinese enterprise users, while the description and triggers are primarily Chinese-language, but the manifest does not state that this locale restriction is optional or justified by a region-specific compliance requirement. This can constitute a language/locale policy issue because the skill appears to force a specific locale context without offering user choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.