Back to skill

Security audit

makernice-setup

Security checks for vulnerabilities and agentic risk

Overview

This setup guide keeps paid media generation under user control, with explicit price checks and spending limits.

Review the Makernice connection permissions and set spending limits before authorizing a test. Started jobs cannot be canceled, and completed outputs blocked by safety review are still charged. This review covers the complete supplied guide, not the external service implementation.

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

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

md
## 4. Run the test after the user agrees

Only call `generate` after the user has seen the price and said yes. If the user already set a budget and told you to go ahead, you may start without asking again as long as `amount_usd` is within that budget; still use `amount_usd`, not the budget, as `max_cost_usd`.

- `max_cost_usd`: required. Use the `amount_usd` the user approved, exactly as returned by `estimate_cost`. The job is refused if the price is higher.
- `request_id`: required and unique for every new job, printable ASCII with no spaces, at most 64 characters, for example `setup-test-boat-1`. A used id can never be reused for a different job.