ClawHub
Back to skill

Security audit

FAQ Support

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Markdown-only workflow for turning user-provided support questions into PDP FAQ copy, with no hidden execution, persistence, or automatic data access.

Before using it with real support exports, remove or anonymize personal customer data and verify any product, warranty, safety, or regulated claims before publishing them on a PDP.

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
97% confidence
Finding

The skill description contains very broad trigger phrases such as common-language cues about people asking repeated questions or stale FAQs, which can cause the agent to invoke this skill in contexts that only loosely relate to support-driven PDP work. Over-broad auto-triggering is dangerous because it can route unrelated user requests into a workflow that asks for support logs, customer transcripts, or PDP rewrites, increasing the chance of inappropriate data handling, privacy exposure, or degraded task selection.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.