ClawHub
Back to skill

Security audit

Agent Pattern Mining

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed workflow for studying agent systems and turning useful patterns into local documentation or skill improvements.

Install this if you want the agent to study other agent tools and write concrete local workflow or skill improvements. Review proposed edits to persistent files such as AGENTS.md, TOOLS.md, MEMORY.md, or skills before accepting them, especially in shared workspaces.

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)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 85)May include surrounding context.

md
- Prefer lean skills: keep `SKILL.md` procedural and move detailed analysis to `references/`.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The invocation guidance says to use this skill 'when asked to learn from Claude Code, Codex, Gemini CLI, Cursor, or any agent framework/repo' and 'when benchmarking agent UX/architecture' or 'turning observed features into OpenClaw skills, workflow upgrades, AGENTS.md updates, or implementation plans.' These conditions are expansive and lack clear boundaries or exclusion examples, increasing the chance of unintended invocation for general research or comparison tasks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.