Back to skill

Security audit

FlowiseAI

Security checks for vulnerabilities and agentic risk

Overview

The FlowiseAI integration is clearly scoped, but its fallback setup executes unverified downloaded software without a separate approval step.

Review and approve the CLI installation separately before allowing setup to run; the downloaded installers were unavailable for inspection. Check the CLI's automatic skill synchronization settings, trust OOMOL with the submitted FlowiseAI data, and retain the skill's confirmation requirement for prediction requests.

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 code executes a remote Oomol installation script rather than performing FlowiseAI operations. Nothing in the supplied chunk establishes this installer as a supporting dependency for FlowiseAI. The remote script's contents and subsequent effects are not provided, so those effects cannot be assessed.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

Piping an HTTPS response directly into bash executes mutable remote content without checking its integrity or reviewing it first. Compromise of the installer distribution path could therefore lead to arbitrary code execution with the invoking user's permissions; HTTPS does not protect against a compromised publisher or distribution server.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

Fallback setup executes remote installation scripts without a system-integrity warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback directs the agent to execute remotely downloaded shell or PowerShell code without an explicit installation approval step or integrity verification. Although this is a legitimate dependency and only applies when the CLI is missing, installation crosses from operating a connector into modifying the local environment with the user's privileges.

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 77)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