ClawHub
Back to skill

Security audit

Instagram Reel Extractor

Security checks for vulnerabilities and agentic risk

Overview

The skill does what it claims by reading an already-open Instagram DM tab for reel links and saving sender/link pairs locally, with a privacy note users should understand before use.

Install only if you are comfortable letting the agent inspect an authenticated Instagram DM tab and write sender IDs plus reel/post links to a local `instagram_reels.csv` file. Review where that CSV will be created and avoid running it on conversations you do not want recorded.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs the agent to append Instagram sender identifiers and reel links to a local CSV file without explicitly warning the user that potentially sensitive social-media data will be persisted on disk. This creates a privacy and data-handling risk because the user may not realize personal data from private DMs is being stored locally and could later be exposed, synced, or misused.

Content

No source excerpt is available for this finding.