Back to skill

Security audit

Stability AI

Security checks for vulnerabilities and agentic risk

Overview

The Stability AI workflow is coherent, but its setup can execute unverified software and make undisclosed changes to other agents’ skills.

Review the setup before installing. Prefer an independently verified CLI release and explicitly approve local installation. The skill does not explain that the CLI can install additional agent skills; the publisher documents OO_SKILLS_SYNC_DISABLED=1 to disable startup synchronization in its [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). Prompts and generated audio pass through OOMOL and Stability AI, with audio uploaded to connector storage. The remote installers were unavailable for inspection; no malicious behavior 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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command installs software from Oomol rather than performing the declared Stability AI operations. No connection establishing this installer as a supporting implementation detail is shown. The downloaded 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
87% confidence
Finding

The only supplied command initiates an oo login flow and has no visible connection to Stability AI. Authentication could support the declared purpose, but this chunk provides no such integration or subsequent Stability AI functionality; its observable purpose is authentication instead.

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 live remote script directly into Bash without pinning its version or verifying its integrity; the PowerShell alternative has the same issue. Compromise of the distribution endpoint or installer could execute arbitrary code with the agent's local privileges and access available credentials or files. Restricting installation to a missing CLI reduces exposure frequency but does not remove the supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 55)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 76)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