ClawHub
Back to skill

Security audit

Follow Up Boss

Security checks for vulnerabilities and agentic risk

Overview

The skill is a legitimate Follow Up Boss API CLI, but it can change CRM data and delete webhooks without extra safeguards.

Install only in environments where the agent should be allowed to read and modify Follow Up Boss CRM data. Use a least-privileged API key if available, avoid exposing production credentials broadly, and treat delete/update commands, especially webhook deletion, as actions that should require explicit human approval.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill documents use of an API key via environment variable and a networked CLI, but it does not declare any explicit tool scope such as allowed-tools or permissions. That omission weakens containment and reviewability: an agent invoking this skill may be granted broader environment and network access than the skill description makes explicit, increasing the risk of secret exposure or unintended outbound API actions.

External Transmission

Medium
Category
Data Exfiltration
Content
*   node fub.js search "john"
 */

const API_BASE = 'https://api.followupboss.com/v1';
const API_KEY = process.env.FUB_API_KEY || '';
const SYSTEM_KEY = process.env.FUB_SYSTEM_KEY || '';
const SYSTEM_NAME = process.env.FUB_SYSTEM_NAME || '';
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
This code performs network requests to the Follow Up Boss API and can send person details, notes, emails, calls, tasks, and webhook data, which may include personal or business-sensitive information. Although the file lists commands, it does not clearly warn users that invoking these commands will transmit supplied data and retrieved CRM records over the network.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The webhook deletion path performs an irreversible destructive action immediately from CLI arguments, with no confirmation prompt, no dry-run mode, and no safeguard against accidental execution. In an agent or automation context, a malformed command or prompt-influenced action could silently remove monitoring or integration hooks, disrupting downstream systems and security visibility.

Static analysis

Detected: suspicious.env_credential_access, suspicious.exposed_secret_literal

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
fub.js:48

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:16