ClawHub
Back to skill

Security audit

Instagram Media Links & Post Insights

Security checks for vulnerabilities and agentic risk

Overview

The scanners classify this skill as benign with medium confidence: they found no AIG issues and the reported concern is that user-provided Instagram URLs are sent to Apify without an explicit privacy notice.

Before installing, consider that the workflow may send your Instagram URLs to Apify for processing, and the scanner reports that this is not clearly disclosed to users. Avoid submitting URLs with sensitive query parameters or access tokens. The scan was partial: it inspected all five listed components but could not resolve one local path-like reference, so the evidence is incomplete.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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 (2)

The workflow submits user-provided URLs to Apify without a user-facing data-sharing notice.

Medium
Category
Output Handling
Confidence
86% confidence
Finding

The instructions require submitting the user's URLs to an Apify Actor and preserving each URL exactly as supplied. Although the skill explains Apify setup and limits processing to public posts, it never explicitly warns users that their supplied URLs will be transmitted to a third-party service; public post URLs can also contain query parameters supplied by the user.

Content

No source excerpt is available for this finding.

The workflow sends the user's exact URLs to a third-party Apify Actor without requiring a user-facing privacy disclosure.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

This step instructs the agent to invoke an Apify Actor with the exact user-supplied URLs, rather than merely listing an available tool. Although the workflow requires announcing that processing will begin, it does not require informing the user that their URLs will be shared with Apify and the selected Actor.

Content

No source excerpt is available for this finding.