Security audit

Taplio LinkedIn Hook Generator

Security checks for vulnerabilities and agentic risk

Overview

The skill uses a disclosed Taplio connection to personalize LinkedIn hooks, find examples, and optionally save an unpublished draft.

Use topics you are comfortable sharing with Taplio, since searches send your topic to that service. Review connector permissions before connecting, and specify whether you want the chosen hook saved as a draft.

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

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 the user's topic to Taplio without explicitly warning about that data transfer.

Medium

Category: Output Handling
Confidence: 91% confidence
Finding: The skill instructs the agent to call search_inspiration(query=topic, ...), transmitting the user-supplied topic to Taplio. Although it discloses the Taplio dependency, it does not explain that the user's topic—which may contain unpublished or confidential information—will be shared with that third-party service.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.