Back to skill

Security audit

Replicate

Security checks for vulnerabilities and agentic risk

Overview

This Replicate skill needs review because its CLI dependency can persistently install skills across other agents without explaining that side effect here.

Review the CLI separately before allowing setup. Prefer an independently verified release and, if cross-agent skill installation is unwanted, set OO_SKILLS_SYNC_DISABLED=1 before invoking it. Understand that OOMOL mediates your connected Replicate account. Replicate mutations have explicit approval safeguards; the material concern is broader dependency behavior. The remote installer remains unverified, and no malicious intent was established.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied code performs remote script installation rather than Replicate operations. Although installing a dependency could be a supporting implementation detail, this chunk provides no evidence that the Oomol installer supports the declared Replicate functionality. The downloaded script's contents and subsequent effects cannot be determined from the supplied code.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The setup command pipes a mutable remote script directly into Bash without checking its contents, version, or integrity; the PowerShell alternative has the same weakness. Compromise of the hosting or delivery infrastructure could execute arbitrary code with the agent's local permissions, exposing accessible files and credentials. Restricting installation to a missing-CLI error reduces exposure but does not establish trust in the downloaded code.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% 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 86)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources