ClawHub
Back to skill

Security audit

browse-products

Security checks for vulnerabilities and agentic risk

Overview

This documentation-only skill coherently provides product search through a disclosed external API, with privacy and affiliate-link notes users should understand before use.

Install only if you are comfortable with product search queries being sent to the documented external API and with results containing outbound or affiliate store links. Avoid putting secrets, account details, or sensitive personal information in search terms.

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

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description uses broad activation language like 'browse a product catalog' and 'find items by description,' which can cause the agent to invoke this skill for ordinary shopping or browsing requests without clearly signaling that user queries will be sent to a third-party service. This increases the chance of over-triggering and unnecessary disclosure of user-provided text to an external API.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill instructs users to submit natural-language queries to an external endpoint but does not warn that search text is transmitted off-platform. Users may include sensitive preferences, personal details, or other private content in queries, creating a privacy risk through uninformed disclosure.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · reference.md (reported line 342)May include surrounding context.

md
For complete response schema, see [API reference](reference.md).

## cURL Examples

### Single search

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · skill.md (reported line 87)May include surrounding context.

md
For complete response schema, see [API reference](reference.md).

## cURL Examples

### Single search

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
74% confidence
Finding

The manifest describes a semantic product search skill with price filtering, pagination, and relevance scoring. Mentioning a /go endpoint used for redirects suggests an affiliate or outbound redirection capability that is not reflected in the manifest's declared purpose of searching and browsing products.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The document presents itself as complete API documentation for semantic product search endpoints, and the listed endpoints only include search and bulk search. However, the error/status code section states that 302 Found is used by a /go endpoint, introducing behavior not otherwise documented and outside the stated endpoint list.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.