ClawHub
Back to skill

Security audit

Feishu Doc Editing

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill gives Feishu document editing guidance with expected live edit and image upload capabilities, but users should confirm targets before modifying documents or uploading local files.

Install only if you intend agents to edit live Feishu documents. Confirm the target document, requested edits, delete operations, and any local image file path before running the workflow, especially when documents contain business or private 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 (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This markdown file instructs the agent to use block-level update, delete, insert, append, and write-avoidance strategies for editing live Feishu documents. Although the skill is clearly about document editing, it does not include any user-facing warning that these actions will modify existing document data and may remove content or formatting.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill instructs use of `upload_image` with a local `file_path` but does not warn that this causes local file contents to be read from the execution environment and transmitted to Feishu. In an agent setting, that omission can lead to accidental exfiltration of sensitive local files if a user or prompt steers the agent toward arbitrary paths.

Static analysis

No suspicious patterns detected.