ClawHub
Back to skill

Security audit

Feishu Send Image

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it sends a user-selected local image to a specified Feishu recipient, but its credential-handling instructions are weaker than they should be.

Install only if you trust the Feishu app and understand that the image will be uploaded to Feishu and sent as the configured bot. Avoid putting the app secret directly in shell history, shared terminals, logs, or screenshots; prefer wrapping the script to read the secret from a protected environment variable or config file, and keep the bot permissions limited to the needed Feishu scopes.

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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
78% confidence
Finding
The skill explicitly instructs users to execute a shell script and therefore has shell execution capability, yet it does not declare any permissions or safety constraints. That gap reduces transparency and prevents proper review of what the skill can access or transmit, which is especially relevant because the documented workflow includes reading local files and sending data to an external API.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The README tells users to pass the Feishu App Secret as a positional command-line argument. Command-line secrets can be exposed through shell history, process listings, terminal logs, CI output, or monitoring tools, which makes credential leakage realistic in normal usage. Because this skill directly uses long-lived bot credentials to call Feishu APIs, exposure could let an attacker send messages as the bot or abuse the associated app permissions.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The documentation tells users to pass the Feishu app secret on the command line and even includes a concrete example containing a secret-like value. Command-line secrets can be exposed through shell history, process listings, logs, and monitoring tools, making credential theft significantly easier. In this context the skill directly uses those credentials to obtain API tokens and send messages, so compromise could enable unauthorized Feishu API access.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.