ClawHub
Back to skill

Security audit

Perplexity

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for using Perplexity through OOMOL, but its fallback setup tells the agent to install the CLI by executing a remote script without checksum, version pinning, or explicit user approval.

Review this before installing if you are uncomfortable with an agent running remote installer scripts. Prefer installing the `oo` CLI yourself from trusted OOMOL documentation or verifying the installer before execution, then use the skill for Perplexity connector actions only when you intend to send data through OOMOL and Perplexity.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The skill instructs the agent to install software by piping a remote script directly into bash, which is a classic supply-chain and arbitrary code execution risk. If the remote endpoint, transport, or distribution pipeline is compromised, the agent could execute attacker-controlled code on the host with the user's privileges.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The instruction to use this skill for ANY Perplexity request is overly broad and can cause the agent to invoke the skill in situations where direct API use, a narrower skill, or additional validation would be safer. Broad auto-selection increases the chance of unintended external calls, expanding exposure to connector-side actions and remote data handling without sufficient task-specific scoping.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The action list marks create_embeddings with [write] at L41, and the Safety section says [write] actions change Perplexity state at L48. But the described behavior of generating embeddings for input strings does not indicate persistent remote state changes; the documentation therefore actively overstates the action's side effects.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.