Back to skill

Security audit

Netlify

Security checks for vulnerabilities and agentic risk

Overview

Netlify changes require approval, but fallback setup executes unverified remote code and can introduce broader changes to your agent tools.

Review and install the CLI separately before allowing this skill to run setup. Consider disabling bundled-skill synchronization using the publisher-documented OO_SKILLS_SYNC_DISABLED setting. Connect only the Netlify account and permissions needed, and retain the skill's approval checks for changes and deletion. Installer contents and hosted connector implementation were not verified; the review found no artifact-backed evidence of intentional deception or exfiltration.

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 (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command executes an Oomol-hosted installation script, with no demonstrated connection to Netlify functionality. This is materially different from the declared purpose, not an established supporting implementation detail. The remote script's contents and further effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The only supplied behavior is a login command for oo, whose connection to Netlify is not established. Authentication could be a supporting implementation detail if it served Netlify, but this chunk provides no evidence of that relationship. The mismatch is the apparent service target, not merely the absence of CRUD operations.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping the HTTPS response directly into bash executes mutable remote content without inspection, version pinning, or independent integrity verification. Compromise of the installer distribution could expose local files and credentials or modify the environment; this is the same underlying installation risk identified by SQP-2, not evidence that the current installer is malicious.

Content

Scanner excerpt · SKILL.md (reported line 74)May include surrounding context.

Fallback setup executes downloaded installation scripts without warning about remote code execution or local system changes.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback setup directs immediate execution of downloaded shell or PowerShell scripts without an explicit installation approval step or independent integrity verification. If the distribution endpoint or delivery pipeline is compromised, this permits arbitrary code execution with the invoking user's privileges; limiting setup to a missing-CLI error reduces exposure but does not remove the risk.

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 95)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