Back to skill

Security audit

Exa

Security checks for vulnerabilities and agentic risk

Overview

The Exa workflow is coherent, but fallback setup immediately runs downloaded installer code without a separate approval step.

Preinstall a trusted, verified CLI version and require approval before allowing fallback installation. Review its automatic skill-sync settings and understand that OOMOL mediates Exa requests and credentials. The concern is uncontrolled setup behavior; the inspected skill does not establish malicious intent or exfiltration.

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
98% confidence
Finding

The supplied command performs remote code execution for an apparent Oomol CLI installation, not an Exa data operation. Nothing in the supplied chunk establishes that this is a supporting implementation step for Exa. The downloaded script's contents are not provided, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
84% confidence
Finding

The supplied chunk performs only a CLI login; it neither targets Exa nor implements the declared data operations. Authentication could be a supporting implementation detail if oo were established as the Exa access mechanism, 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 a live HTTPS download directly into bash executes mutable remote code without a pinned version or independent integrity verification. If the installer host or distribution pipeline is compromised, the script could access local data or modify the system with the executing account's privileges; the legitimate CLI dependency does not eliminate this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

The setup workflow instructs the agent to execute remote installation scripts without warning the user about the system-integrity implications.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback setup directs execution of downloaded shell or PowerShell code without requiring user approval or explaining that it can modify the local system with the agent's privileges. Triggering setup only when the CLI is absent reduces exposure, but installation remains a significant trust boundary beyond an ordinary Exa request.

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 79)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