Back to skill

Security audit

Mutual Fund Evaluator

Security checks for vulnerabilities and agentic risk

Overview

This financial-analysis skill appears purpose-aligned, but it sends sensitive investor profile data to an external AI/web-search service without enough privacy or data-handling disclosure.

Review this before installing if you are uncomfortable sending personal financial context to a hosted third-party service. Avoid entering account numbers, PAN/tax IDs, exact holdings, or other identifiers unless the publisher provides clearer privacy, retention, and third-party processing terms.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill requests sensitive financial profiling data such as age, risk tolerance, tax sensitivity, and existing portfolio details while also advertising web search integration, but it provides no privacy notice, data handling explanation, or warning that user inputs may be transmitted to external services. In a finance context, this omission can lead users to disclose personal financial information without informed consent, increasing privacy and compliance risk.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 157)May include surrounding context.

md
## References

- **Kong Route:** https://api.toolweb.in/tools/mutual-fund-evaluator
- **API Docs:** https://api.toolweb.in:8205/docs

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description states the API is for "Indian retail investors," which is a locale/market-specific constraint expressed in natural language. In this file there is no indication that users can opt into this locale targeting or that the regional restriction is explicitly justified as a compliance-bound or region-specific tool.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The endpoint explicitly states it uses AI with web search, but the schema provides no warning that submitted investor profile data may be transmitted to third-party search or AI services. Users may provide sensitive financial context under the assumption processing is local, creating a meaningful privacy and data-governance risk if external services receive fund names, portfolio details, goals, or risk preferences.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The description says the tool is for Indian retail investors, which imposes a locale-specific scope in the natural-language skill definition. Because the documentation does not present this as a user-selectable locale or clearly justify it as a region-specific tool, it may conflict with language/locale neutrality expectations.

Content

No source excerpt is available for this finding.