ClawHub
Back to skill

Security audit

Parallel Search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Parallel web-search helper; it uses an external authenticated CLI as expected, with no hidden code, persistence, or destructive behavior found.

Install only if you are comfortable sending search queries and related task context to Parallel through its authenticated CLI. Avoid using it for secrets, credentials, private internal details, or local-only lookup tasks unless you intentionally want external web search.

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
Confidence
95% confidence
Finding
The skill description advertises search capability but does not clearly disclose that user queries are transmitted to an external provider (Parallel API/CLI). This lack of transparency can lead to unintended disclosure of sensitive prompts, internal project details, or personal data when users or agents assume the operation is local.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger phrases are broad enough to match many normal user requests like 'look up' or 'find online', which increases the chance this skill auto-invokes in situations where the user did not clearly consent to using an external search provider. In this skill's context, that matters because invocation can cause user queries to be sent to a third-party web/API service and may expose sensitive or contextual data unnecessarily.

Static analysis

No suspicious patterns detected.