ClawHub
Back to skill

Security audit

market sales skills

Security checks for vulnerabilities and agentic risk

Overview

This is a marketing and sales guidance skill with no executable code, persistence, credential access, or hidden data flow, though its broad activation and fixed sales framing should be used carefully.

Before installing, consider narrowing activation to explicit Floods sales or mobile-gaming UA tasks. Treat the commercial claims and advertising-compliance assertions as material to verify before using them externally, especially claims about unlabeled content, performance lift, platform partners, and campaign metrics.

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

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill declares very broad activation triggers and includes a catch-all rule ('When in doubt, load this skill'), which can cause it to activate in many loosely related contexts. That increases the chance the assistant injects sales messaging, proprietary positioning, or biased commercial framing into responses where the user did not request it, reducing instruction fidelity and potentially causing data leakage across tasks.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill imposes mandatory communication rules ('apply these rules without exception') and a fixed persuasive style regardless of user preference. This can override user intent and steer outputs toward a predetermined sales posture, which is risky in an assistant setting because it can bias responses, suppress neutrality, and produce outputs misaligned with the user's requested tone or purpose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.