Back to skill

Security audit

Clerk

Security checks for vulnerabilities and agentic risk

Overview

Clerk operations have clear approval safeguards, but setup executes unverified remote code and leaves broader agent changes insufficiently disclosed.

Review setup before installing. Install a verified CLI release yourself and review or disable its automatic skill synchronization; the vendor documents OO_SKILLS_SYNC_DISABLED for that purpose in its [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). Connecting Clerk entrusts OOMOL with access to your Clerk account. Keep the required approvals for account changes and deletion. The supplied skill shows no malicious intent, but the remote installer and hosted implementation were not verified.

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
99% confidence
Finding

The supplied command installs software from an Oomol domain rather than performing Clerk data operations. No connection to Clerk is shown that would establish this as a supporting implementation detail. The contents and further effects of the remote script are not available in the supplied chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The fallback installation command streams a mutable remote script directly into Bash without inspecting it or verifying its integrity; the PowerShell alternative has the same problem. A compromised distribution endpoint could execute arbitrary code with the agent's local privileges, exposing accessible files and credentials. The missing-CLI condition limits when this occurs but does not mitigate the execution risk.

Content

Scanner excerpt · SKILL.md (reported line 65)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 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