Security audit

Taplio LinkedIn Smart Comment Writer

Security checks for vulnerabilities and agentic risk

Overview

This skill drafts LinkedIn comments through Taplio and requires explicit approval before scheduling a public comment under your name.

Connecting Taplio allows the skill to read account preferences and relevant LinkedIn content and save drafts. Review the wording and language before approving scheduling: publication may occur later, and the MCP cannot recall a posted comment.

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 skill forces the post's language over the user's language preference without opt-in.

Medium

Category: Output Handling
Confidence: 99% confidence
Finding: The instruction explicitly requires matching the post's language even when it differs from the user's default. It provides neither a user choice nor a documented justification requiring that language override.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.