Back to skill

Security audit

Feishu Doc

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small Feishu document integration that discloses read and write document operations and does not include executable code or persistence.

Install this only if you want the agent to work with Feishu documents. Because the skill can modify remote documents, users should ask for previews and give explicit approval before create, update, or append actions, especially for shared or business documents.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly supports create, update, and append operations against Feishu documents but does not warn that these actions will modify remote user data. This can lead to unintended destructive or privacy-impacting changes if an agent invokes the skill without clearly signaling side effects or obtaining explicit user confirmation for write operations.

Content

No source excerpt is available for this finding.