Back to skill

Security audit

Taplio LinkedIn Trending Topics Scanner

Security checks for vulnerabilities and agentic risk

Overview

The skill uses disclosed Taplio profile settings and searches to suggest LinkedIn topics, with no instructions to publish or change account content.

Your Taplio profile preferences inform the recommendations, and niche keywords become Taplio search queries; request generic terms if your positioning is confidential. Review connector permissions: Taplio's broader connector supports publishing and deletion, although this skill does not invoke them. Taplio documents browser authorization and revocable access in its [official connector documentation](https://github.com/TaplioOfficial/taplio-linkedin-mcp).

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
Vulnerability Patterns
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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 workflow sends user-specific niche keywords to Taplio without a privacy disclosure.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The workflow instructs the agent to extract keywords from the user's profile settings and submit them as search queries to the third-party Taplio service. Although the Taplio dependency is documented, the skill does not warn that user-specific profile information will be included in outgoing queries.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.