ClawHub
Back to skill

Security audit

Agent Harness

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed engineering workflow skill with broad activation language, but the artifacts do not show hidden execution, exfiltration, destructive behavior, or unsafe persistence.

Install this if you want an agent workflow that pushes planning, testing, checkpoints, and limited subagent coordination. Be aware it may activate for broad coding words like build or debug, so users who prefer narrower skill routing may want the description tightened.

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
97% confidence
Finding
The manifest description contains a long, highly generic set of triggers such as 'build', 'plan', 'review', 'ship', and 'debug'. In systems that use description text for routing or auto-invocation, these broad terms can cause the skill to activate in many unrelated contexts, increasing the chance of inappropriate workflow takeover, tool use, or interference with safer/more specific skills.

Static analysis

No suspicious patterns detected.