Back to skill

Security audit

TikTok: post & schedule videos and photo carousels (1Social)

Security checks for vulnerabilities and agentic risk

Overview

The skill provides disclosed, user-approved social posting through 1Social with clear controls for uploads and publication.

Connect only the accounts you intend to use and check the destinations, media and timing before approving. Uploaded local files become public immediately, and published TikToks require manual removal. Publishing after the trial requires a paid plan.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

The TikTok-specific skill also instructs the agent to publish to seven other social networks.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The manifest describes publishing and managing posts on the user's TikTok account. These instructions explicitly enable simultaneous publication to Instagram, LinkedIn, X, Threads, Facebook Pages, YouTube Shorts, and Bluesky by selecting multiple channel IDs, expanding the publication destinations beyond the declared TikTok scope. The confirmation step mitigates unintended posting but does not resolve the description-behavior mismatch.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 74)May include surrounding context.

md
- **Unschedule:** `cancel_post`. Use this, not `delete_post`, for a post that has not been published.
- **Delete a published post:** `delete_post`, only after the user confirms. Report per network what actually came down: Instagram, TikTok, Threads and YouTube posts stay live and only the user can remove them.
- **A delivery failed:** `retry_delivery` retries one network and spends quota again. It is refused for permanent failures such as a revoked connection — then the user must reconnect at https://1social.dev/app.
- **A delivery is `unknown`:** ask the user to look at the network. Only when they tell you whether the post is live, call `confirm_delivery` with their answer. Never guess, and never `retry_delivery` with `force` without asking — it may publish a second copy.