Back to skill

Security audit

Hubspot Audit

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a real HubSpot audit skill, but it handles a sensitive CRM token and follow-on code contribution actions with weaker safeguards than users should accept by default.

Before installing, treat this as a Review item: use a dedicated least-privilege read-only HubSpot private app token, provide it through a secure environment or secret store rather than saving it to .env, and review any generated report before sharing it. Run dependency installation in an isolated environment with pinned versions. Do not allow the skill to create new skills, commit code, push to a fork, or open a pull request unless you explicitly want that separate development workflow.

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)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:17
Finding

Plaintext Storage of a HubSpot Private-App Token

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
SKILL.md:22
Finding

Unpinned Runtime Installation of Third-Party Python Packages

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill instructs the agent to create a new skill, fork a repository, commit code, push to a fork, and open a pull request when an uncovered issue is found. Those software supply-chain actions are outside the scope of a HubSpot audit and can lead to unauthorized code changes, data leakage into commits/PRs, or abuse of the agent's development credentials if followed automatically.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill directs broad collection and analysis of CRM records across contacts, companies, deals, engagement, and deliverability, but provides no privacy, minimization, or retention guidance. Because CRM data commonly contains personal and business-sensitive information, omission of handling constraints raises the risk of over-collection, unnecessary exposure in generated reports, and noncompliant processing.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill tells the agent to ask for a HubSpot private app token and store it in a local .env file. Persisting secrets to workspace files increases the chance of accidental exposure through logs, reports, backups, commits, or later reuse by unrelated tasks, especially in an agent environment handling multiple workflows.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill handles a sensitive HubSpot private app token without warning the user about credential sensitivity or safe handling practices. In practice, this can normalize unsafe secret sharing and storage, increasing the likelihood of credential compromise and subsequent unauthorized CRM access.

Content

No source excerpt is available for this finding.