ClawHub
Back to skill

Security audit

Parallel Extract

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed URL extraction helper for Parallel's API, with no evidence of hidden code, persistence, or unrelated data access.

Install only if you are comfortable sending requested URLs and extracted page content to Parallel's service. Avoid using it for internal, authenticated, confidential, or legally restricted pages unless you have confirmed that third-party extraction is appropriate.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The description does not warn users that URLs and potentially retrieved page content will be sent to Parallel's external API for processing. This creates a transparency and privacy risk, especially if users provide internal, sensitive, authenticated, or otherwise confidential URLs under the assumption that processing is local.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are broad enough to match routine user requests like reading a URL or fetching a page, which can cause the skill to activate in many normal contexts without clear user awareness. Because this skill sends requested URLs and extracted content to an external service, overbroad triggering increases the chance of unnecessary data disclosure and unintended third-party processing.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.