ClawHub
Back to skill

Security audit

competitor-research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward SEO competitor research guide with no executable code, persistence, credential handling, or hidden behavior.

Before installing, expect the skill to guide an agent to use web search, competitor pages, and possibly your own project or analytics data when you provide or authorize it. Review any private business files or analytics exports before sharing them, but the skill itself does not add code execution or persistent access.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description says to use the skill whenever the user wants to analyze competitors for SEO, content, backlinks, or positioning, which is a wide natural-language trigger without clear boundaries for when this skill should be used versus adjacent skills. Although a few example phrases are listed, the activation scope still lacks explicit exclusion conditions beyond a single note about content roadmap, increasing the risk of unintended invocation.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The phrase 'On first use, if helpful' leaves unclear when the introductory behavior should occur and when it should not, which creates inconsistent activation and response behavior. This kind of discretionary wording makes the skill's invocation and execution conditions less predictable.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.