ClawHub

Feishu File Sender

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it sends a selected local file to Feishu using the configured OpenClaw Feishu account, with no hidden persistence or extra destinations found.

Install this only if you want agents on this machine to send local files to Feishu. Keep ~/.openclaw/openclaw.json protected, limit the Feishu app permissions where possible, and verify the file path and chat or user ID before sending sensitive files.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill documentation declares runtime behavior that reads local files, accesses environment variables, and makes outbound network requests, but it does not declare corresponding permissions. This creates a transparency and policy-enforcement gap: users or the platform may grant trust to the skill without realizing it can access local configuration and transmit data externally.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The script can exfiltrate an arbitrary local file to an external Feishu recipient with no interactive warning, confirmation, dry-run, or destination/file summary before transmission. In an agent-skill context, this is more dangerous because an automated workflow may invoke it on sensitive files or with attacker-influenced receive IDs, causing unintended external disclosure.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal