Security audit

Monkeytype Tracker and Advisor

Security checks across malware telemetry and agentic risk

Overview

This Monkeytype stats skill is purpose-aligned and disclosed, but users should handle the required API key carefully and understand optional scheduled reports.

Prefer setting MONKEYTYPE_APE_KEY yourself instead of pasting the ApeKey into chat or storing it in plaintext. Only enable daily or weekly reports if you want recurring local jobs, and delete ~/.openclaw/workspace/config/monkeytype.json or rotate the ApeKey if you uninstall the skill or no longer trust the local machine.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Rogue AgentSelf-Modification, Session Persistence
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection

Findings (9)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 95% confidence
Finding: The skill performs privileged actions such as reading environment variables, writing a config file, and making network requests, but it does not declare those permissions. This creates a transparency and consent problem because users and the hosting system cannot accurately assess what the skill will access or modify before use.

Context-Inappropriate Capability

Medium

Confidence: 86% confidence
Finding: The skill expands from on-demand stats retrieval into persistent scheduled execution by instructing creation of cron jobs. Scheduled tasks increase operational risk because they create recurring execution, ongoing network access, and persistence on the user's system beyond the immediate user request.

Description-Behavior Mismatch

Low

Confidence: 85% confidence
Finding: The skill stores configuration and cached Monkeytype results locally, but this persistence behavior is not clearly disclosed in the manifest. Undisclosed local storage can expose user activity history and automation preferences to other local processes or users, especially if file permissions are not restricted.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The setup flow asks the user to paste their Monkeytype ApeKey directly into chat without a strong warning that it is a secret credential. Secrets shared in chat may be logged, retained, or exposed to unintended components, making credential compromise more likely.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill persists the user's ApeKey to a local config file after receiving it, but the flow does not prominently explain the security implications of storing credentials on disk. Local plaintext secret storage raises the risk of later disclosure through filesystem access, backups, or other tools reading the file.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The setup flow explicitly tells the agent to save the user's ApeKey to a config file without warning the user that a credential will be persisted on disk. Storing API credentials in plaintext files increases the chance of credential disclosure through local compromise, backups, logs, or accidental sharing of workspace files.

Ssd 3

Medium

Confidence: 98% confidence
Finding: Instructing the user to paste an API key directly into the conversation is a credential-handling anti-pattern. Even if the key is only for Monkeytype, it still grants account-level API access and could be misused if captured from logs or transcripts.

Ssd 3

Medium

Confidence: 96% confidence
Finding: The skill directs the agent to persist a user-supplied API key after receiving it in chat, compounding exposure by both collecting and storing the credential. This increases the number of places the secret may exist, which broadens the attack surface for accidental leakage or unauthorized retrieval.

Session Persistence

Medium

Category: Rogue Agent
Content: - Linux/Mac: `export MONKEYTYPE_APE_KEY="YOUR_KEY_HERE"` **Option 2: Config File** Create this file: `~/.openclaw/workspace/config/monkeytype.json` With this content: { "apeKey": "YOUR_KEY_HERE"
Confidence: 88% confidence
Finding: Create this file: `~/.openclaw/workspace/config/monkeytype.json` With this content: { "apeKey": "YOUR_KEY_HERE" } Then just say "monkeytype stats" and I'll take it from there! ``` After receiving

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.