ClawHub
Back to skill

Security audit

diagnose

Security checks for vulnerabilities and agentic risk

Overview

This is a debugging workflow skill that is broad in when it may activate, but its instructions are coherent, disclosed, and aligned with diagnosing bugs.

Install this if you want a more formal debugging process. Expect it to spend extra effort building reproductions, running tests or harnesses, and sometimes using parallel sub-agents for complex bugs; for quick typo-level fixes it may be more process than you need.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says to use the skill whenever the user 'reports a bug' or says something is 'broken / throwing / failing / flaky / hanging / leaking,' even without explicitly asking for the skill. These are common phrases in ordinary troubleshooting conversation, and the file does not provide clear exclusion boundaries beyond a brief note about trivial cases, increasing the risk of unintended invocation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The 'When to use this skill' section includes generic conditions like a user reporting a bug, showing an error log, or asking why something failed. While examples are provided, the criteria remain broad and could overlap with routine explanation requests or lightweight troubleshooting, with only limited exclusion text for tiny fixes and non-bug questions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.