ClawHub
Back to skill

Security audit

trust-badges-generator

Security checks for vulnerabilities and agentic risk

Overview

This is a simple design-guidance skill for trust badges, with no executable code, persistence, credential access, or hidden behavior.

Before installing, be aware that the skill may activate for some broad social-proof requests; otherwise it is limited to trust badge placement advice and should be safe to use as ordinary design guidance.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description uses very broad trigger terms such as "trust badges," "trusted by," "security badges," and "social proof," which can match many unrelated user requests and cause the skill to activate when not intended. Over-broad activation increases the chance the agent applies this skill in the wrong context, leading to irrelevant guidance or interference with more appropriate skills, especially because it also overlaps with adjacent domains like press logos, hero sections, testimonials, and brand protection.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.