Back to skill

Security audit

Fly.io

Security checks for vulnerabilities and agentic risk

Overview

The Fly.io controls are sensible, but setup can run unchecked downloads and introduce changes to other agents’ installed skills without clear approval.

Review setup before installing. Install a reviewed CLI release yourself and consider disabling its startup skill synchronization with OO_SKILLS_SYNC_DISABLED=1, as documented by the publisher. Use a narrowly scoped Fly.io connection and retain the required approvals for cloud changes. Installer contents and hosted credential handling were not independently verified; 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
  • 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 runs an Oomol-hosted installer, not a Fly.io operation. Nothing in the code establishes that this installation supports the declared Fly.io functionality. Executing this unrelated remote installer is a material mismatch; the installer’s additional behavior cannot be determined from the supplied chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
82% confidence
Finding

The supplied chunk only invokes an authentication command and contains no identifiable Fly.io integration or data operations. Authentication could be a supporting implementation detail if oo were established as a Fly.io interface, but the supplied content provides no such connection.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an unpinned HTTPS download directly into Bash executes whatever the remote endpoint supplies without prior inspection or independent integrity verification. A compromised distribution endpoint or malicious installer update could execute code with the user's privileges, exposing local credentials and files; the legitimate dependency relationship does not eliminate this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

First-time setup executes downloaded installer scripts without warning about local system changes or remote-code execution.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback directs the agent to execute remotely downloaded installers without requiring explicit approval for local installation or explaining that they can run arbitrary commands with the invoking user's privileges. Limiting this behavior to a missing CLI reduces exposure, but the confirmation requirements for Fly.io state changes do not cover these local system changes.

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 84)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