Security audit

MongoDB Atlas Administration

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches a MongoDB Atlas read-only connector purpose, but its setup instructions include unverified remote installer commands that execute immediately.

Review this skill before installing. Its normal Atlas project and cluster reads are coherent, but do not run the documented installer one-liners unless you trust OOMOL's installer path and are comfortable executing changing remote code on your machine; prefer a verified, pinned, or manually reviewed CLI installation method.

A.I.G

Vulnerability Patterns

Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

Findings (1)

T03 · Remote Payload Retrieval and Execution

Error

Location: SKILL.md:58
Finding: Unverified Remote Installer Download and Execution
Content: View full analysis
Remediation: View remediation
/install.sh" echo " oo-installer.sh" | sha256sum --check less oo-installer.sh bash oo-installer.sh ``` Equivalent integrity verification and explicit execution steps should be required on Windows. ]]>

SkillSpector

Vulnerability Patterns

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

External Script Fetching

High

Category: Supply Chain
Confidence: 98% confidence
Finding: The skill instructs users to install software by piping a remotely fetched script directly into a shell (curl ... | bash), which is a classic supply-chain and remote code execution risk. If the host, CDN, DNS, TLS trust chain, or upstream script is compromised, the user will execute attacker-controlled code immediately, and because this skill is for administration workflows, that code may run in an environment with access to sensitive tooling and connected accounts.
Content: Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

oo: command not found — install the oo CLI (other platforms: https://cli.oomol.com/install-guide.md):

bash
curl -fsSL https://cli.oomol.com/install.sh | bash # macOS / Linux

powershell

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The manifest and description frame the skill as suitable for 'searching and reading data,' but the body explicitly discusses support for state-changing Atlas administration actions. This mismatch can cause an orchestrator or user to invoke the skill under the false assumption that it is read-only, increasing the risk of unintended administrative changes if additional write actions are later exposed or already exist via the connector.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger text says to use this skill for 'ANY MongoDB Atlas Administration request,' which is overly broad and may capture tasks beyond the narrow read-oriented actions listed. In an agent setting, broad routing language can cause unintended invocation in contexts where the skill is inappropriate, potentially leading to credentialed access to sensitive project and cluster metadata without sufficient task scoping.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.