ClawHub
Back to skill

Security audit

agent-search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a very small wrapper for listing agents and does not include hidden code, network behavior, persistence, or destructive actions.

Before installing, confirm that agent-browser is a tool you expect to have available and that you are comfortable with a skill that may be offered whenever the agent thinks listing agents is relevant. The artifact is minimal, so users should rely on the installed agent-browser command's provenance for deeper assurance.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill metadata is overly broad: the description says only 'List all agents' and the trigger constraints are effectively unspecified because read_when is empty. This can cause the agent framework to surface or invoke the skill in contexts beyond its intended scope, increasing the chance of unnecessary shell-tool exposure and unintended enumeration behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.