ClawHub
Back to skill

Security audit

security-test-suite

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a disclosed web monitoring tool, but it documents authenticated live checks and mutating HTTP methods without enough in-skill safeguards for credentials or production targets.

Install only if you will use it on systems you own or have written authorization to monitor. Use test or least-privilege credentials, avoid passing real session cookies when possible, configure proxies carefully, and override endpoint methods to avoid POST, PUT, or DELETE unless the target is designed for safe testing.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly supports authenticated checks via cookies, bearer tokens, API keys, custom headers, and proxies, but provides no warning that supplied credentials will be transmitted to the target service and may be sent to unintended hosts if the target or proxy is misconfigured. In an agent context, this omission can lead users to run live authenticated scans against production systems without understanding the credential exposure, authorization, and audit implications.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The documentation describes availability checks, port connectivity testing, SSL monitoring, and endpoint verification across multiple HTTP methods, but does not warn that these actions actively probe live systems and may trigger monitoring, rate limits, WAFs, or violate acceptable-use boundaries if run without authorization. Because this is a monitoring/scanning skill, lack of operational warnings increases the chance of accidental unauthorized or disruptive use by an agent or operator.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.