ClawHub
Back to skill

Security audit

economic-moat

Security checks for vulnerabilities and agentic risk

Overview

This business-analysis skill needs review because it directs the agent to save real-use lessons in its reusable instructions without clear privacy controls.

Before using confidential company information, remove the recurring save instruction at SKILL.md:101 or require explicit approval and generalized, sanitized lessons. Review saved changes before sharing the skill. No malicious code or data-exfiltration instruction was found.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

Instructs persistent recording of real-use failure patterns without a user-facing warning.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The instruction to add entries 'after each real use' and 'paste the actual failure pattern' encourages retaining session-derived information in the reusable skill document without requiring user consent or sanitization. Because this skill handles investment, acquisition, and business-strategy discussions, those entries could expose confidential information to later users or repository readers if saved or shared; however, the file does not explicitly request secrets, automatic publication, or external transmission.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.