ClawHub
Back to skill

Security audit

nanobot-feishu-send

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small Feishu attachment-sending guide for nanobot, with expected local-file upload behavior and no executable code or persistence.

Before installing, understand that paths placed in media cause the actual local file contents to be uploaded to Feishu and shared with the current or specified chat. Confirm the file content, recipient/chat_id, and avoid sending secrets, credentials, config files, or private documents by mistake.

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README explains how to send local files through Feishu but does not clearly warn users that the referenced local paths will cause the actual file contents to be uploaded to an external messaging platform. In a skill specifically designed for attachment sending, this omission increases the risk of accidental data exfiltration, especially if users assume only a path reference or local action is involved.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly instructs the agent to send arbitrary local files from the machine running nanobot to a Feishu chat, but it provides no warning, consent check, or data-sensitivity guardrails. In an agent setting, this can enable inadvertent exfiltration of local documents, media, or other sensitive files if a user request or prompt causes the agent to reference confidential paths.

Content

No source excerpt is available for this finding.