Back to skill

Security audit

OpenStatus

Security checks for vulnerabilities and agentic risk

Overview

OpenStatus changes require approval, but the CLI setup can execute unverified code and introduce persistent agent skills beyond the stated task.

Review the CLI installer and its additional agent-skill installation behavior before proceeding. The publisher documents startup synchronization controls in its [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). Connect only the intended OpenStatus account through OOMOL and retain the skill's approval requirements for changes and deletions. Review is warranted by the setup scope; no malicious behavior was established.

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 command installs software from Oomol, with no visible OpenStatus interaction or evidence that this installation supports the declared functionality. Remote script execution is a material capability absent from the description. The fetched 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

The setup instructions pipe a remotely fetched, unpinned script directly into Bash without reviewing or independently verifying its contents; the PowerShell alternative uses the same download-and-execute pattern. Compromise of the distribution endpoint or publishing pipeline could therefore execute arbitrary code with the invoking user's permissions, exposing local files and credentials. Its restriction to missing-CLI setup reduces exposure, but does not remove the supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 63)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 84)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