ClawHub
Back to skill

Security audit

KOL Roi

Security checks for vulnerabilities and agentic risk

Overview

This is a focused KOL ROI analysis skill with no code execution, persistence, or hidden data access, though users may share sensitive business performance exports with it.

Install only if you want structured creator ROI and renewal analysis. Treat pasted order, refund, affiliate, Shopify, and GA4 exports as sensitive business data, and remove unnecessary customer identifiers before sharing them.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
93% confidence
Finding

The skill description contains expansive trigger language such as activating on vague requests like 'which KOL is worth keeping' or when users paste messy exports. This can cause the skill to be invoked in situations where the fit is uncertain, leading to misrouting, overcollection of business data, or low-quality analysis based on incomplete context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

The instruction requires a table with 'exactly these column headers (English),' which imposes a language requirement on every response. Because the file does not offer user opt-in or explain a justified region-specific need for English output, this is a natural-language locale policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.