ClawHub
Back to skill

Security audit

系统化调试四阶段方法论

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown debugging workflow that is broad in activation scope but does not add hidden code, persistence, credential access, or unrelated behavior.

Install this if you want the agent to follow a disciplined debugging process. Expect it to spend time reproducing issues, reading files, running tests or diagnostic commands, and sometimes suggesting temporary instrumentation before making fixes. Review use on non-debugging technical requests because its activation wording is broad.

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
Confidence
95% confidence
Finding
This markdown file defines when the skill should be used, and the phrase "Use for ANY technical issue" is broad enough to overlap with a wide range of ordinary troubleshooting requests. The surrounding examples help somewhat, but they do not provide limiting conditions or negative examples that clearly distinguish when this skill should not activate.

Static analysis

No suspicious patterns detected.