ClawHub
Back to skill

Security audit

内容合规预检

Security checks for vulnerabilities and agentic risk

Overview

This compliance helper needs review because some livestream advice could leave viewers misled while helping a streamer avoid scrutiny.

Review or replace the livestream incident-response section before relying on this skill. Require clear, prompt corrections and evidence for medical, financial, and promotional claims. The static scan reported no findings, but that does not resolve the problematic advice. The scanner's partial status reflects missing referenced files, which I confirmed are absent; automated scanning claims remain unverified.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

The incident-response sequence disguises concealment of misleading claims as routine compliance handling.

Medium
Category
Prompt Injection
Confidence
97% confidence
Finding

The response procedure explicitly recommends covering misleading statements with new speech, avoiding explanations, and preventing pauses because they could attract platform scrutiny. In a compliance-advice skill, this can cause the agent to present concealment as remediation, leaving viewers with uncorrected medical, financial, or promotional claims; the broader emphasis on truthful advertising does not neutralize these instructions.

Content

No source excerpt is available for this finding.