Back to skill

Security audit

Apify

Security checks for vulnerabilities and agentic risk

Overview

The Apify workflow is coherent, but its automatic setup can execute unreviewed software and introduce broader agent changes without clear user approval.

Review and approve CLI installation separately, and confirm actor inputs and potential costs. Understand that OOMOL handles the Apify connection. Upstream documents OO_SKILLS_SYNC_DISABLED=1 to prevent additional agent-skill writes in its [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). Remote installers remain unverified; no installer was executed.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied command installs or bootstraps software through an Oomol-hosted script; it shows no Apify data operations or established dependency on this installer. Executing this unrelated remote installer is a material departure from the declared purpose. The downloaded script's contents and further effects are not visible in the supplied chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an unpinned HTTPS response directly into bash executes whatever the installation endpoint supplies without an independent integrity check or review. Compromise of that endpoint or its delivery infrastructure could yield arbitrary code execution with the agent's privileges; the PowerShell installation example presents the same risk.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

The setup workflow executes remotely downloaded installation scripts without warning about local system changes.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The fallback directs the agent to execute downloaded installation scripts without requiring approval for local software installation or explaining potential system changes. A missing CLI could therefore turn an Apify request into execution of remote code with the agent's local privileges; the conditional trigger reduces exposure but does not establish user consent.

Content

No source excerpt is available for this finding.

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 80)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