ClawHub
Back to skill

Security audit

Competitor Intelligence

Security checks for vulnerabilities and agentic risk

Overview

This skill provides competitive research prompts and has no executable code, persistence, credential use, or hidden installation behavior.

Installers should treat outputs as research aids, use only lawfully available public information, avoid collecting personal or non-public data, respect site terms, and ask the agent to cite and verify sources for complaints, pricing, tech stack, and competitor claims.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly directs users to gather competitors' review complaints and detect visible tech stacks, but it provides no guardrails around lawful collection, privacy boundaries, source reliability, or acceptable-use limits. In a competitive-intelligence context, this can encourage misuse such as scraping restricted sources, mishandling personal data, or producing inaccurate or ethically problematic intelligence for sales and marketing decisions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.