ClawHub
Back to skill

Security audit

aidelly-social-autopilot

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Aidelly social-posting reference that can publish to live accounts, but its capabilities are disclosed and aligned with its purpose.

Install only if you intend to let an agent operate Aidelly social workflows. Treat create, schedule, approve, and media-upload calls as real actions against connected social accounts; preview content carefully and use approval-required scheduling when possible.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill documents an immediate-publish capability to external social platforms without a prominent user warning that invoking the tool can cause real-world, irreversible outbound actions. In an agent setting, this increases the risk of accidental posting, reputational harm, and unintended disclosure if a user or upstream prompt does not fully realize the operation is live rather than draft-only.

Missing User Warnings

Low
Confidence
90% confidence
Finding
The media upload section states that the service fetches media from a provided public URL but does not clearly warn users about the privacy and data-handling implications of causing a third-party service to retrieve remote content. This can lead to unintended disclosure of URL-hosted assets, tracking beacons, or sensitive-but-public links being shared with the service without informed user awareness.

Static analysis

No suspicious patterns detected.