ClawHub
Back to skill

Security audit

Free Tool Strategy

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable marketing strategy skill with some broad trigger wording and privacy-guidance gaps, but no hidden behavior or unsafe runtime authority.

Review the privacy implications before following its lead-capture advice: collect only necessary information, make email capture optional or clearly disclosed where possible, and ensure consent and legal compliance. Also expect the skill may activate broadly around free-tool or lead-generation discussions.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description says to use this skill when the user wants to "plan, evaluate, or build a free tool" and even "whenever someone wants to build something useful and give it away," which is broad enough to overlap with many ordinary product, engineering, or content discussions. Although some examples are specific, the activation scope is not tightly bounded and lacks exclusion conditions, increasing the risk of unintended invocation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly recommends lead capture and 'email collection' but provides no guidance on consent, minimization, retention, or applicable privacy rules. In context, this can lead downstream users to design data-collection flows that are non-compliant or overly invasive, creating privacy, legal, and reputational risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This JSON eval file is a manifest-type file, so vague-trigger checks apply. The expected behavior and assertion explicitly state the skill should 'trigger on casual phrasing,' which is ambiguous and broad enough to overlap with ordinary user requests, increasing the risk of unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.