ClawHub
Back to skill

Security audit

Monday For Agents

Security checks for vulnerabilities and agentic risk

Overview

This monday.com skill is mostly purpose-aligned, but it includes under-disclosed handling of a monday.com API token and an unpinned local MCP package that would receive that token.

Review before installing. Prefer the hosted OAuth MCP option or a pinned, reviewed local MCP version. Do not place a live monday.com API token directly in openclaw.json or other plaintext files; use the platform's secret/environment mechanism and a least-privilege monday.com account. Treat TOOLS.md board IDs as workspace-specific internal metadata.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T08 · Insecure Dependencies

Warning
Location
skill.md:217
Finding

Unpinned MCP Package Execution

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
skill.md:221
Finding

Plaintext API Token in MCP Configuration

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
Findings (12)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · skill.md (reported line 39)May include surrounding context.

md
### Get an API Token

1. Log into monday.com as the agent.
2. Click avatar → **Developers** → **My Access Tokens** → **Copy**.
3. Set the token as an environment variable via OpenClaw's config (preferred) or your system's secret manager.
   ❌ Do **not** write the token to a plaintext file or add it to shell startup files.
   ❌ Do **not** commit tokens to version control.

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · skill.md (reported line 87)May include surrounding context.

md
fi

monday_query() {
  RESPONSE=$(curl -s -X POST "$MONDAY_API_URL" \
    -H "Content-Type: application/json" \
    -H "Authorization: $MONDAY_API_TOKEN" \
    -H "API-Version: 2024-10" \

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest description says 'Use when' followed by a wide range of activities including creating, connecting, querying, updating, and troubleshooting. This broad natural-language trigger scope lacks explicit boundaries or exclusion conditions, making unintended invocation more likely for general monday.com-related conversations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The phrase 'One skill for everything monday.com' is expansive and nonspecific, implying the skill should activate for any monday.com mention. Because it does not define scope limits or unsupported cases, it creates ambiguity about when the skill should or should not be used.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · skill.md (reported line 71)May include surrounding context.

Monday.com uses a single GraphQL endpoint:

text
https://api.monday.com/v2    (preferred)
https://api.monday.com/graphql  (also works)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · skill.md (reported line 72)May include surrounding context.

Monday.com uses a single GraphQL endpoint:

text
https://api.monday.com/v2    (preferred)
https://api.monday.com/graphql  (also works)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · skill.md (reported line 78)May include surrounding context.

Monday.com uses a single GraphQL endpoint:

text
https://api.monday.com/v2    (preferred)
https://api.monday.com/graphql  (also works)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · skill.md (reported line 87)May include surrounding context.

md
fi

monday_query() {
  RESPONSE=$(curl -s -X POST "$MONDAY_API_URL" \
    -H "Content-Type: application/json" \
    -H "Authorization: $MONDAY_API_TOKEN" \
    -H "API-Version: 2024-10" \

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
99% confidence
Finding

The local MCP example embeds MONDAY_API_TOKEN directly in JSON as "your_token_here", normalizing hardcoded secrets in a config file. That increases the chance the token is stored on disk, leaked through backups or logs, or accidentally committed to version control, giving an attacker API access to monday.com data.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

Persisting workspace and board IDs in a plaintext TOOLS.md file can expose internal metadata to later prompts, other users, or tooling that reads the repository/workspace. While IDs are not equivalent to credentials, they can aid enumeration, targeting, and accidental cross-context operations, especially in multi-tenant agent environments.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

Earlier setup guidance explicitly says not to write the monday API token to a plaintext file and to store it in the OpenClaw environment or a secret manager. The troubleshooting table then tells the user to 'update file' for a regenerated token, which conflicts with the documented secret-handling approach and could mislead users into storing credentials in files.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The guidance instructs the user to write to TOOLS.md using shell redirection, which modifies a local file. Although the action is minor and operationally useful, this section does not explicitly warn that it will create or change local state in the repository or workspace.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.