Security audit

Taplio LinkedIn Audience Persona Builder

Security checks for vulnerabilities and agentic risk

Overview

The skill uses a clearly disclosed Taplio connection to research a LinkedIn audience and create a persona, with appropriately limited instructions.

Taplio is required and receives audience-role and pain-point search terms. Keep those terms generic or anonymized, avoid confidential customer information, and review the connector permissions before connecting.

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 user-derived audience details to Taplio without a privacy warning.

Medium

Category: Output Handling
Confidence: 90% confidence
Finding: The required search_inspiration call transmits the persona's role and core pains to Taplio as a search query. Although the skill discloses its Taplio dependency, it does not warn that details derived from the user's answers or actual customers may be sent to that third-party service.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.