Back to skill

Security audit

Instagram: post & schedule posts, Reels and carousels (1Social)

Security checks for vulnerabilities and agentic risk

Overview

The skill supports user-approved social publishing with clear safeguards and disclosed limits on uploads and post removal.

Review the connected accounts and approve every destination before publishing. Approved local uploads become publicly accessible even if you cancel the post. Published Instagram posts must be removed manually, and 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)

L64–L66 expand the Instagram-only skill into publishing across seven additional social networks.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The manifest at L03 describes publishing and managing Instagram content. L66 explicitly instructs the agent to select additional channel IDs and publish simultaneously to TikTok, LinkedIn, X, Threads, Facebook Pages, YouTube Shorts and Bluesky, enabling public writes beyond the stated network scope.

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 75)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 Instagram posts, but the workflow states that Instagram posts cannot be deleted through this skill.

Low
Category
Excessive Agency
Confidence
99% confidence
Finding

L03 explicitly lists deleting Instagram posts as a supported use. However, L57 and L73 state that published Instagram posts remain live and must be removed by the user, contradicting the advertised management capability.

Content

No source excerpt is available for this finding.