Security audit

Pingdom

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a Pingdom reading connector, but its setup asks users to execute an unverified remote installer and its scope is broader than a read-only Pingdom helper should be.

Review before installing. Use this skill only for the listed read-only Pingdom actions unless future documentation clearly declares write actions and confirmation requirements. Do not pipe the installer directly into a shell; prefer a pinned, verifiable oo CLI release or inspect and verify the installer before running it. Be aware that OOMOL will mediate Pingdom requests and that setup may create persistent local and account-level state.

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 Installation Scripts Executed Directly by the Shell
Content: View full analysis
Remediation: View remediation

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)

Description-Behavior Mismatch

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The manifest and description constrain the skill to 'searching and reading data,' but the body explicitly discusses possible [write] and [destructive] actions. That mismatch weakens policy and user expectations, making it easier for an invoking agent or user to authorize this skill under a read-only assumption while the skill contract implicitly permits state-changing operations.
Content: No source excerpt is available for this finding.

External Script Fetching

High

Category: Supply Chain
Confidence: 99% confidence
Finding: The skill instructs users to execute a remote installation script via 'curl ... | bash', which is a classic supply-chain and arbitrary code execution risk. If the remote endpoint, transport, distribution pipeline, or hosting account is compromised, users may execute attacker-controlled code directly on their machine.
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

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrase 'Use this skill for ANY Pingdom request' is overly broad and can cause the agent to invoke the skill in contexts beyond its intended safe scope. Broad auto-routing increases the chance that sensitive, administrative, or unintended tasks are funneled through the skill without sufficient user awareness or task-specific validation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.