ClawHub
Back to skill

Security audit

Consumer Insights

Security checks for vulnerabilities and agentic risk

Overview

The skill is only a Markdown instruction file, but it asks for broad business documents and context while its stated purpose is much narrower customer feedback analysis.

Review this skill carefully before installing. It does not execute code or install anything, but its instructions are much broader than its stated feedback-analysis purpose and may encourage users to paste sensitive internal business or customer information. Use only redacted feedback text and avoid secrets, personal data, confidential documents, or regulated material.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill is advertised as sentiment analysis for user feedback, but the documentation expands it into broad market research, operations optimization, process automation, strategic decision support, and generation of ready-to-use deliverables. This scope drift can cause unsafe routing and over-delegation of business-critical tasks to a loosely defined skill, increasing the chance that users provide sensitive data or rely on outputs beyond the skill's intended safeguards and competence.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill solicits business context, documents, requirements, and stakeholder information but does not warn users about sensitive, confidential, personal, or regulated data handling. In this context, the absence of a privacy/data-minimization warning is dangerous because customer feedback and business materials commonly contain PII, proprietary information, and contract or regulatory details that users may paste into the skill unnecessarily.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The input guidance asks users to paste broad 'business context, data, or requirements' and lists expansive categories without defining acceptable inputs or use boundaries. That makes the skill easy to invoke for unrelated or high-risk tasks and encourages submission of excessive internal information, which can lead to misuse, data oversharing, and reliance on outputs in contexts the skill was not designed to handle.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.