Back to skill

Security audit

Octave

Security checks for vulnerabilities and agentic risk

Overview

The Octave integration fits its purpose, but setup can execute remote code and introduce broader agent changes without clear approval.

Review the CLI installation and its changes to other agent skills before allowing setup. Prefer a reviewed, pinned installation, connect only the intended Octave workspace, and retain confirmation for data changes. Requests pass through OOMOL. The remote installer contents and hosted connector implementation were not verified; the concerns support review, not a conclusion of malicious intent.

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
97% confidence
Finding

The supplied command performs remote software installation, not Octave data operations. Nothing in the provided content establishes Oomol as a supporting dependency for Octave. The downloaded script is not supplied, so its further behavior cannot be assessed.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a remote installer directly into Bash executes mutable network-delivered code with the invoking user's privileges, without a pinned version or independent integrity verification. A compromised distribution endpoint could therefore execute arbitrary commands and access local data or credentials; HTTPS and the legitimate dependency relationship do not eliminate that supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

The setup workflow instructs the agent to execute downloaded installation scripts without warning the user about remote code execution or system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback directs the agent to install software through remotely supplied shell or PowerShell code without requiring approval for local system changes. Restricting installation to a missing-CLI error reduces exposure, but a request to operate Octave does not necessarily authorize installing software on the host.

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 86)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