Back to skill

Security audit

Taplio LinkedIn Content Calendar Planner

Security checks for vulnerabilities and agentic risk

Overview

This LinkedIn calendar skill uses disclosed account access and requires confirmation before changing drafts and approval before scheduling posts.

Use explicit LinkedIn planning requests. Connecting Taplio lets the assistant read your profile and unpublished drafts. Confirming the calendar permits draft creation and revision of reused backlog drafts; review each post and its scheduled time before approval, since scheduling leads to automatic publication.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Generic trigger phrases can activate the LinkedIn planning workflow for unrelated requests.

Medium
Category
Trigger Abuse
Confidence
96% confidence
Finding

Unqualified triggers such as "plan my month" can select this LinkedIn-specific workflow for unrelated planning requests. Because the skill requires an immediate get_me call before clarification, mistaken activation can cause unnecessary account-data access or divert the user into Taplio setup. Confirmation before draft creation and per-draft approval before scheduling substantially limit the consequences; the trigger alone does not authorize posting.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.