Back to skill

Security audit

Elorus

Security checks for vulnerabilities and agentic risk

Overview

The Elorus workflow requires approval for changes, but its setup can execute unverified remote code and introduce additional agent skills without explaining those effects.

Review and install a verified CLI version before use. Consider disabling its startup skill synchronization with OO_SKILLS_SYNC_DISABLED=1, as documented in the linked CLI reference. Connect only the necessary Elorus account and permissions, and review invoice changes carefully. The remote installer and hosted connector implementation were not audited.

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 chunk contains no Elorus API access or data operations. Instead, it runs an external installer. Although dependency installation can be a supporting implementation detail, this chunk establishes no relationship between the Oomol installer and the declared Elorus functionality. The downloaded script's contents and subsequent effects cannot be determined from the supplied code.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The setup instructions pipe a mutable remote script directly into Bash without version pinning or independent integrity verification; the PowerShell alternative has the same fetch-and-execute risk. Compromise of the installer distribution could execute arbitrary commands with the invoking user's privileges and access local files or credentials. The legitimate dependency relationship and missing-CLI-only trigger reduce exposure but do not remove the supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 66)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 87)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