ClawHub
Back to skill

Security audit

Agent Well-Known Readiness Audit

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed workflow for checking public agent/API readiness with optional paid x402 backend calls and an optional local installer.

Install only if you want this readiness-audit workflow. Review the fixed backend, keep wallet spend limits and approval controls in place for x402 payments, use the optional installer with a specific target directory, and avoid --force unless replacing an existing copy is intentional.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill declares no permissions, yet the analysis indicates capabilities for environment access, file read/write, network, and shell. That mismatch is dangerous because callers may treat the skill as low-risk while it can perform materially more powerful actions, increasing the chance of unexpected local modification, data exposure, or command execution during use or installation.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding
The described purpose is a remote readiness audit, but the detected behavior includes local installation, overwrite/delete operations, lock-file creation, checksum handling, and use of a hardcoded backend rather than auditing an arbitrary user-supplied target. This is dangerous because users may invoke the skill expecting a passive audit, while it can change the local system state and make trust decisions based on fixed packaged data, creating supply-chain, integrity, and unintended modification risks.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.