Back to skill

Security audit

Threads: post & schedule posts (1Social)

Security checks for vulnerabilities and agentic risk

Overview

The skill supports user-approved social posting with clear safeguards for public uploads, publishing, and deletion limits.

Connect only accounts you intend to use and review every publishing destination. Approved uploads become publicly accessible immediately, even if you cancel the post. Published Threads posts require manual removal, and continued 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 (3)

The workflow expands a Threads-only skill into multi-network publishing.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The manifest at L03 describes publishing and managing Threads posts. L61–L63 additionally instruct the agent to publish simultaneously to Instagram, TikTok, LinkedIn, X, Facebook Pages, YouTube Shorts and Bluesky, extending public-write operations beyond the advertised network.

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 72)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.

The manifest advertises deleting Threads posts, but the documented implementation cannot delete them.

Low
Category
Excessive Agency
Confidence
99% confidence
Finding

L03 lists deleting Threads posts as a supported use. L55 explicitly states that published Threads posts cannot be deleted through 1Social, and L70 confirms they remain live after the delete operation, contradicting the advertised capability.

Content

No source excerpt is available for this finding.