ClawHub
Back to skill

Security audit

Find

Security checks for vulnerabilities and agentic risk

Overview

This is a simple search-workflow skill that tells the agent how to clarify, search, validate, and report results, without adding code, persistence, credential access, or hidden behavior.

Before installing, consider that this skill may make the agent more likely to perform iterative searches for vague find-style requests. It appears appropriate for locating specific items, but users should still provide constraints such as source, budget, location, time, and success criteria.

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
94% confidence
Finding

The skill’s activation examples and usage criteria are broad enough to match many ordinary requests like 'find me' or 'where can I get,' which can cause the agent to invoke this skill in situations where a simpler or safer path would be more appropriate. Over-broad triggering increases the attack surface by allowing untrusted prompts to steer the agent into iterative searching, source expansion, and possible external lookups more often than intended.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.