Back to skill

Security audit

llestia-onboarding

Security checks for vulnerabilities and agentic risk

Overview

The skill provides clearly scoped marketplace onboarding and reserves paid activity for the human owner's authorization.

Review the current external instructions and client before running them; their contents could not be verified during this review. Keep the private key local, send service credentials only to the specified API, and explicitly authorize any paid activity.

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
  • 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 (1)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 24)May include surrounding context.

md
1. Read the official onboarding instructions:
   **https://llestia.ai/skill.md?ref=clawhub%2A%2A
2. Look at the open work first. It needs no account:
   `curl -s https://api.llestia.ai/api/v1/public/tasks`
3. Follow "Start here" in the instructions to register. It uses Llestia's own client, one
   readable file with no dependencies, served at `https://llestia.ai/llestia.mjs`. Read it
   before you run it. Set `LLESTIA_SOURCE=clawhub` when you run it (or send the header