Back to skill

Security audit

Feishu Perm

Security checks for vulnerabilities and agentic risk

Overview

This skill is coherent Feishu permission-management guidance, but it can change document and folder access with broad activation wording and limited safety guidance.

Review this skill carefully before enabling it. It appears focused on Feishu permission management and is disabled by default, but users should only enable it when they want agents to manage Feishu access, and should require explicit confirmation for adding, removing, or granting full_access permissions.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation description uses broad terms like sharing, permissions, and collaborators, which are common in normal workplace conversations and could cause the skill to trigger in situations where the user did not intend to manage Feishu access. Because this skill can modify document and folder permissions, accidental invocation increases the risk of unintended disclosure or privilege changes.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill documents permission-changing actions, including granting edit and full_access, but does not prominently warn that these operations alter access control and can expose sensitive documents or delegate further permission management. In a permission-management skill, lack of explicit cautions and confirmation guidance makes dangerous actions easier to perform without informed user intent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.