ClawHub
Back to skill

Security audit

Drata

Security checks for vulnerabilities and agentic risk

Overview

The Drata reads fit the stated purpose, but the required CLI can also make lasting changes to other agents’ installed skills without explaining those effects here.

Review the CLI separately before installing. Use a reviewed, fixed release and consider setting OO_SKILLS_SYNC_DISABLED=1 before invoking it, as documented in the [CLI reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). Connect Drata with read-only access and ensure you accept OOMOL handling sensitive records. The remote installers and live connector implementation remain unverified.

A.I.G

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

SkillSpector

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 performs remote software installation rather than Drata data access. Nothing in the chunk establishes that this installer is a supporting dependency for the declared functionality. The downloaded script's contents and further effects are not provided, so those effects cannot be assessed.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The installation command streams a mutable remote script directly into Bash without verifying its integrity or authenticity beyond HTTPS; the PowerShell alternative has the same execution pattern. If the installer endpoint or its delivery infrastructure is compromised, invoking this fallback could execute attacker-controlled code with the agent process's permissions, exposing accessible files and credentials; restricting it to missing-CLI errors reduces exposure but does not eliminate the risk.

Content

Scanner excerpt · SKILL.md (reported line 62)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 83)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