Back to skill

Security audit

Check

Security checks for vulnerabilities and agentic risk

Overview

The Check functions fit the stated purpose, but setup can execute unverified remote code and introduce broader persistent changes to agent skills.

Review and approve the CLI installation separately before allowing automatic setup. OOMOL mediates Check requests and receives their inputs. If you only want this integration, review or disable the CLI's broader skill synchronization; the [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md) documents OO_SKILLS_SYNC_DISABLED. The downloaded installers were not inspected, so their exact local effects remain uncertain.

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
98% confidence
Finding

The supplied command performs remote script execution rather than searching or reading Check data. Nothing in the supplied chunk establishes that installing this external CLI is a supporting requirement for Check access. The downloaded script's contents and further effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

Piping a live HTTPS download directly into bash executes whatever the installer endpoint supplies, without a pinned version or independent integrity verification; the PowerShell alternative has the same weakness. If the distribution endpoint or delivery pipeline is compromised, attacker-controlled code could run with the agent process's local privileges and access its files and credentials.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

The setup workflow executes remotely downloaded installation scripts without warning the user about local system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

A missing CLI causes the workflow to instruct installation without first obtaining approval for executing remote code and changing the local environment. This expands a Check data-reading request into software installation; the conditional setup trigger limits exposure but does not establish user authorization.

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 78)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