Back to skill

Security audit

Analyze Creator Financial Health with Automated Reporting

Security checks for vulnerabilities and agentic risk

Overview

The skill is not visibly malicious, but it asks for broad financial and reporting access without enough scoping or safety guidance.

Review this skill carefully before installing. Use test or read-only credentials where possible, limit each API key to the minimum required permissions, avoid sharing full financial reports to broad Slack channels, and confirm any Airtable or Slack destination before enabling recurring reports.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 7)May include surrounding context.

md
_SECRET"],"bins":["python3","curl"]},"os":["macos","linux","win32"],"files":["SKILL.md"],"emoji":"💰"}}

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest declares only Stripe and PayPal secrets plus basic binaries, but the body documents additional integrations including Google Analytics, Slack, Airtable, WordPress, affiliate platforms, and other external services. This mismatch can mislead users and reviewers about the true data-access scope, making informed consent, least-privilege review, and sandbox policy decisions harder for a skill handling sensitive financial data.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill encourages users to connect financial accounts and automate reports to Slack without warning that sensitive revenue, transaction, and cash-flow information may be transmitted to third-party platforms. In this context, the omission is risky because financial data is commercially sensitive, and Slack channels/workspaces may have broader visibility, retention, or app access than intended.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill's stated purpose is financial analysis, but the documentation extends it to Slack-based reporting and Airtable storage, which introduces secondary exfiltration and persistence channels for highly sensitive business data. Expanding capabilities beyond core analysis increases attack surface and the chance that revenue, cash-flow, and account details are sent to less-controlled third-party systems.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The Slack reporting example instructs sending recurring financial reports to a workspace/channel without advising users to validate recipients, channel privacy, app permissions, or data sensitivity. Because the reports include revenue totals, projections, runway, and top performers, an incorrect or overly broad destination could leak valuable internal financial intelligence.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The setup instructions tell users to export live API keys and service-account JSON directly in environment variables without any guidance on secure secret handling, scoping, rotation, or avoiding logs/history exposure. For payment processors and analytics accounts, compromised credentials could enable unauthorized access to financial records, reporting data, and connected services.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.