ClawHub
Back to skill

Security audit

Buffer API

Security checks for vulnerabilities and agentic risk

Overview

The Buffer skill is coherent, but it can publish, edit, reorder, and delete social posts with a Buffer API key without explicit confirmation guardrails for destructive actions.

Review before installing if you will connect a real Buffer account. Use a limited Buffer API key where possible, keep it in a controlled environment variable, and require explicit human confirmation for create, edit, move, and especially delete operations on scheduled or draft posts.

SkillSpector

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
90% confidence
Finding
The skill clearly requires network access and use of an API key from the environment, but it does not declare permissions or explicitly bound those capabilities. That mismatch can lead hosts or users to underestimate what the skill can access, reducing informed consent and weakening policy enforcement around secrets and outbound requests.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The skill advertises deletePost capability but provides no warning, confirmation, or guardrails for destructive actions. In an agent context, this increases the chance that an LLM or automation flow could delete scheduled or draft content unintentionally, causing business disruption or loss of user work.

Static analysis

No suspicious patterns detected.