Security audit

2pr.io LinkedIn

Security checks for vulnerabilities and agentic risk

Overview

This skill manages social posts through 2pr.io and requires explicit approval for publishing, scheduling, replying, and deleting.

Connect only accounts you intend to manage. Check the profile, destination platform, final text, and scheduled time before approving actions. Review 2pr.io's privacy policy before sending confidential drafts, and revoke access in Preferences when no longer needed.

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

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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

The skill includes publishing and scheduling on X despite its LinkedIn-only manifest description.

Medium

Category: Excessive Agency
Confidence: 96% confidence
Finding: The manifest at L03 describes LinkedIn content management, but L37 explicitly directs the agent to use x_publish and x_schedule to cross-post to X. Requiring a user request limits unauthorized use, but this still adds public posting on another platform beyond the declared scope.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.