Back to skill

Security audit

Edvisage Social Kit

Security checks for vulnerabilities and agentic risk

Overview

This social-posting skill is not destructive, but it promotes making AI-run accounts look non-automated and avoiding automation signals.

Install only if you are comfortable with an agent receiving public social-posting guidance that emphasizes appearing non-automated. Require explicit user approval for posts, disclose automation where required, and follow each platform's spam, bot, and account rules.

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
  • 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
97% confidence
Finding

The skill explicitly advertises 'anti-detection posting patterns' and elsewhere recommends randomization and avoidance of predictable patterns that signal automation. That encourages evasion of platform bot-detection and policy enforcement, increasing the likelihood of deceptive behavior, account sanctions, and misuse for astroturfing or spam at scale.

Content

No source excerpt is available for this finding.