Back to skill

Security audit

Financial Health Check Analyzer

Security checks for vulnerabilities and agentic risk

Overview

This is a descriptive financial-planning skill with no hidden execution, network access, persistence, or transaction authority, but users should avoid sharing raw account details unnecessarily.

Installers should treat this as informational financial guidance only. Do not provide account numbers, full statements, names, addresses, or unredacted merchant-level records unless needed; aggregated categories and balances are usually enough. Consult a qualified financial professional before acting on major financial, tax, investment, or debt decisions.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The requirement 'Clear documentation in English' imposes a specific language in natural-language policy without offering opt-in or documenting a justified regional limitation. This can violate language/locale policy because it constrains output language for all users by default.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README explicitly instructs users to export and analyze three months of bank transaction history, which is highly sensitive financial data, but provides no guidance on minimization, redaction, secure handling, retention, or consent. In a financial-analysis skill, this omission increases the chance that users will paste or upload raw account data unnecessarily, creating privacy exposure and possible downstream leakage to logs, third-party systems, or the model context.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger section is broad enough to match many ordinary finance requests, which can cause the skill to activate in contexts beyond a narrowly scoped 'financial health check.' Over-broad invocation increases the chance of inappropriate routing, overcollection of sensitive financial details, and users receiving generalized financial guidance when they may need more specific, policy-constrained handling.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger keywords include very generic terms such as "financial", "health", "check", and "analyzer", which are likely to match ordinary user requests unrelated to this specific skill. This can cause unintentional invocation or routing collisions with other skills, increasing the chance of inappropriate handling of user input and reducing predictability of agent behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file mixes one English example with predominantly Chinese descriptions and responses, effectively steering usage toward a specific language without stating that the skill is Chinese-only or offering user choice. Under the language/locale policy, forcing or implicitly constraining language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The document is primarily in English but includes a full scenario and expected output in Chinese without stating that multilingual output is optional or user-selected. This can be interpreted as imposing a locale/language mode without an explicit language choice mechanism or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest sets the skill language to "en" with no indication that users may opt into other languages or that the English-only restriction is required for a region-specific or compliance reason. This can violate language/locale policy when a skill imposes a language constraint without user choice or clear justification.

Content

No source excerpt is available for this finding.