ClawHub
Back to skill

Security audit

competitor-profiling

Security checks for vulnerabilities and agentic risk

Overview

This skill performs disclosed competitor research using scraping and SEO tools, with output saved locally for audit and reuse.

Before installing, expect this skill to make external scraping and SEO requests and to save raw competitor research files in your project. Use quick scan for broad lists, confirm before deep profiling or comparing against your own domain, and review/delete raw data if it contains sensitive, copyrighted, or unnecessary review content.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 24)May include surrounding context.

md
3. **Depth level** — quick scan (key facts only) or deep profile (full research)
4. **Focus areas** — any specific dimensions to prioritize (e.g., pricing, positioning, SEO strength, content strategy)

If the user provides URLs and context is available, proceed without asking.

---

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly instructs the agent to persist raw scrapes, SEO responses, and review data to disk by default, but it provides no notice, consent step, retention limit, or sanitization guidance. This creates a real data-handling risk because stored artifacts can contain personal data, account details, proprietary research inputs, or licensed third-party content that may later be exposed, reused out of context, or committed to source control.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill directs scraping third-party review sites and storing representative quotes, ratings, and counts without any privacy, copyright, terms-of-service, or data-use safeguards. Even if the target is competitor intelligence, copying and persisting user-generated review content can capture personal information and create compliance or downstream disclosure risks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The tool reference directs extensive third-party scraping, crawling, searching, SEO lookups, and technology detection but does not disclose that the skill will perform external network access, potentially high-volume collection, or cost/rate-limited operations. This lack of transparency can lead to unanticipated data transfer, billing, and operational impact, especially in multi-competitor or deep-profile runs.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The documentation recommends discovering additional competitors via DataForSEO, which broadens collection beyond the input set the user supplied. While useful for research, this changes the task from profiling known competitors to autonomous market discovery, increasing the chance of unexpected external queries, extra cost, and outputs the user did not authorize.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The reference explicitly instructs using domain intersection against the user's domain, which expands scope beyond profiling the provided competitor URLs into analysis of the user's own site. This can cause unauthorized or unexpected collection/use of first-party business intelligence if the user did not request self-vs-competitor comparison, creating scope creep and privacy/consent concerns.

Content

No source excerpt is available for this finding.