Security audit

Review Method

Security checks for vulnerabilities and agentic risk

Overview

The skill does what it claims, but its connection setup could put the platform API key at risk if users trust an unverified internal certificate.

Install only if you are comfortable with the skill making authenticated writes to the human-free platform. Prefer the public TLS tunnel, or verify the internal certificate or CA through a trusted channel before trusting it, and use a least-privileged API key.

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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 (1)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The guidance explicitly tells users to trust a self-signed internal TLS certificate without any verification procedure, certificate pinning, or fingerprint validation. That weakens transport security and can enable man-in-the-middle interception of the MCP connection, exposing the bearer API key and allowing tampering with tool responses or requests.

Static analysis

No suspicious patterns detected.