Back to skill

Security audit

Magic Hour

Security checks for vulnerabilities and agentic risk

Overview

The Magic Hour workflow has sensible approval controls, but its setup instructions can execute unverified remote software without separate user approval.

Review and approve CLI installation separately, using a verified release and checking whether it installs additional agent skills. OOMOL will mediate access to your connected Magic Hour account; retain the required confirmations for generation, uploads, and deletion. The remote installers and hosted connector implementation were not verified in this review.

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 performs remote software installation rather than any demonstrated Magic Hour operation. Nothing in the provided chunk establishes the Oomol installer as a supporting dependency for Magic Hour. The downloaded script's further behavior is not visible, so no additional capabilities are inferred.

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 remotely retrieved, unpinned script directly into Bash; the PowerShell alternative similarly evaluates downloaded code. A compromised distribution endpoint or malicious installer update could execute arbitrary code with the agent's local privileges, potentially accessing files and credentials; HTTPS and the legitimate dependency relationship do not establish installer integrity.

Content

Scanner excerpt · SKILL.md (reported line 96)May include surrounding context.

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

Medium
Category
Output Handling
Confidence
94% confidence
Finding

When the CLI is missing, the skill directs installation without requiring informed approval for executing remote code and changing the local environment. Its confirmation rules address Magic Hour writes and deletions, not local software installation; the missing-command condition limits when this occurs but does not establish user authorization.

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 117)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