Back to skill

Security audit

Instagram Real Phone Poster

Security checks for vulnerabilities and agentic risk

Overview

This skill can publish to your Instagram account, but its instructions make the promised approval step optional.

Review before installing: require approval of the exact media, caption, account and timing before any test post or scheduled publication. Understand that Nodo receives your media and hosts your Instagram session. Verify setup permissions and how to stop schedules and revoke access; the external setup guide could not be checked. No bundled malicious code was found.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

The workflow makes pre-publication approval optional despite the manifest promising approval before anything goes live.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The description promises approval before anything goes live, but the workflow makes review optional and provides no explicit approval gate before publishing or scheduling. An agent following these instructions could publish content without the approval the user expected, potentially exposing private media or causing reputational harm on the user's real Instagram account.

Content

No source excerpt is available for this finding.