ClawHub
Back to skill

Security audit

notworking

Security checks for vulnerabilities and agentic risk

Overview

This skill is an outage-checking helper, but it can automatically share failed URLs or service names with a third-party service, so users should review the privacy scope before installing.

Install only if you are comfortable with agents sending failed target identifiers and failure categories to notworking.io. Avoid using it for private, internal, authenticated, payment, booking, or user-specific URLs unless the agent sanitizes the target first and you explicitly approve the report.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description is broad enough to trigger on many routine failures ('site', 'URL', 'skill', 'MCP server', timeouts, blocks, login issues) without a tight activation boundary. That can cause the agent to invoke this skill in many contexts and automatically send third-party status checks and reports about user activity, increasing privacy, unnecessary network calls, and the chance of sharing sensitive target URLs or service metadata.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.