ClawHub
Back to skill

Security audit

free-tools

Security checks for vulnerabilities and agentic risk

Overview

This skill gives marketing strategy guidance for free lead-generation tools and does not include code, persistence, privilege changes, or hidden data movement.

Installers should be aware that this skill may activate on generic tool-building language and may read local product-marketing context files when present. That behavior is disclosed and aligned with its marketing strategy purpose; review the trigger wording if you want stricter routing.

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
96% confidence
Finding

The skill uses very broad trigger phrases such as "calculator," "generator," "interactive tool," and "free resource," which can match many ordinary user requests outside the narrow intended scope of engineering-as-marketing. This can cause the agent to invoke the skill in unrelated contexts, pulling in irrelevant instructions and external context files, which increases the risk of misrouting, prompt confusion, and unintended data access within the agent environment.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The eval explicitly rewards the skill for 'triggering on casual phrasing' but does not define boundaries that distinguish valid free-tool requests from adjacent domains. This can cause over-broad routing or activation, leading the agent to apply the wrong skill to vague marketing requests and produce unreliable or policy-bypassing behavior through misclassification.

Content

No source excerpt is available for this finding.