Back to skill

Security audit

Ragie

Security checks for vulnerabilities and agentic risk

Overview

Ragie changes require approval, but the required CLI can also silently install or refresh skills across other agents.

Review the CLI’s additional skill installation behavior before proceeding. Its documentation provides OO_SKILLS_SYNC_DISABLED=1 to disable startup synchronization; set it before invoking oo if you only want Ragie access. Review the installer separately and understand that OOMOL mediates account access. The remote installer and exact installed CLI version remain unverified.

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 (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied code performs remote script execution from an Oomol domain rather than any visible Ragie operation. Nothing in the supplied chunk establishes this installer as a supporting dependency for the declared Ragie functionality. The downloaded script's further behavior cannot be determined from this chunk.

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 fetched, mutable script directly into Bash without integrity verification or review; the PowerShell alternative follows the same download-and-execute pattern. A compromised distribution endpoint or malicious installer update could execute arbitrary code with the invoking user's permissions, potentially exposing local files and credentials. Conditional execution only when the CLI is missing reduces exposure frequency but does not remove this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 73)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 94)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