ClawHub
Back to skill

Security audit

troubleshooting-guide-writer

Security checks for vulnerabilities and agentic risk

Overview

The bundled skill has limited local access and explicit safety rules, although its helper checks input fields rather than producing the promised troubleshooting guide.

Treat the helper's output as an input-validation report; a qualified reviewer must complete and verify any service guide against the manufacturer's manual. Use a dedicated output folder to avoid overwriting an existing result. The optional unsigned Windows app is unnecessary for the documented Python workflow and falls outside this assessment.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The material mismatch is in the primary output, not the supporting file operations. Although the code recognizes fields such as diagnostic_steps, safety_notes, and escalation, it only reports whether they are populated and within character limits. The output named troubleshooting-guide.md contains validation results and generic guardrails, not the guide promised by the description. No network access or other unrelated capability is evident.

Content

No source excerpt is available for this finding.

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 30)May include surrounding context.

md
## The job

Experienced technicians fix faults from memory, so new hires call the senior tech for every problem, and the written steps that do exist skip the safety limits that caused a near miss.

## What you get

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The skill produces a brief-validation report rather than the troubleshooting guide promised by its manifest.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The manifest promises a troubleshooting guide with ordered diagnostic steps, safety limits, and escalation triggers. The implementation outputs only field lengths, missing-field notices, and generic guardrails; it neither includes the supplied field contents nor generates diagnostic steps or escalation instructions, despite naming the output troubleshooting-guide.md.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.