ClawHub
Back to skill

Security audit

Agent Harness

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed engineering workflow guide, with no executable payload or hidden data behavior found.

Use this skill when you want stricter engineering discipline from an agent. Review its broad activation wording if you prefer narrow routing, and expect it to guide the agent toward running verification commands, writing checkpoint/output files, and using limited subagents for larger tasks.

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
92% confidence
Finding

The trigger list uses broad phrases like 'engineering workflow', 'build protocol', and 'coding discipline' without clear scope boundaries, which can match loosely related requests. In an agent-routing context, ambiguous triggers increase the chance of incorrect invocation, unnecessary tool use, and degraded safety or usability through misclassification of tasks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger list uses broad phrases like 'engineering workflow', 'build protocol', and 'coding discipline' without clear scope boundaries, which can match loosely related requests. In an agent-routing context, ambiguous triggers increase the chance of incorrect invocation, unnecessary tool use, and degraded safety or usability through misclassification of tasks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.