ClawHub
Back to skill

Security audit

chargebee

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chargebee billing integration with high-impact capabilities, but it consistently requires user approval and least-privilege handling before writes, automation, or credential use.

Install this only if you intend to manage Chargebee billing through Maton. Use read-only or least-privilege Chargebee access when possible, verify the connection ID before actions, and require explicit confirmation for any billing write, hosted function, trigger, or persistent destination.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This Chargebee skill bundles a large GitHub trigger reference that is unrelated to the skill’s stated billing-administration purpose, materially expanding the documented automation surface to include GitHub event payloads containing private repository data, personal data, and installation identifiers. Even though the text claims it is shared reference material, including it in this skill can mislead an agent or user into treating GitHub-triggered data flows as part of the Chargebee skill, creating unnecessary cross-domain access patterns and increasing the risk of unintended data exposure.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The trigger examples use America/Los_Angeles as the default timezone in documented commands and sample output, which can steer behavior toward a specific locale without user opt-in. Under the policy, locale-specific defaults should either be user-selectable or clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The file explicitly says it 'does not widen' the skill scope, yet it provides detailed GitHub trigger payload schemas and automation inputs that could still be consumed by an agent or workflow builder. That mismatch is dangerous because security boundaries in agent systems are often shaped by what documentation is co-packaged and discoverable, so inaccurate scope claims can cause over-trust and accidental use of unrelated sensitive inputs.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.