Back to skill

Security audit

Industry Roi Calculator

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Chinese-language ROI report generator with no evidence of hidden access, persistence, or data exfiltration.

Reasonable to install for Chinese-language presales ROI estimates. Treat results as rough business estimates, validate inputs before sharing reports externally, and avoid passing attacker-controlled free-form text into reports that will be rendered or published without review.

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Note
Location
src/generator.js:367
Finding

Unescaped CLI Input Allows Markdown and Terminal Output Injection

Content
View full analysis
Remediation
View remediation
-])/g, '\\$1'); } ``` 5. Reject missing option values and malformed arguments instead of silently accepting them. 6. Add tests covering newline injection, Markdown headings, links, ANSI escape sequences, unsupported industries, and unsupported scenarios. ]]>
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

This JavaScript file generates all user-facing report content and command-line help exclusively in Chinese, including headings, labels, warnings, and parameter descriptions. Because the skill does not provide any mechanism for language selection or indicate that it is intentionally limited to a Chinese-only regional context, it violates the language/locale policy for natural-language content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

This code embeds user-facing expectations and report assertions entirely in Chinese, such as report headers and scenario names, implying the skill output is fixed to a specific language. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The usage string instructs users to supply example values in Chinese (e.g. "零售", "客服") with no indication that other languages are supported. This can constitute a language/locale policy issue because it implicitly constrains user interaction to a specific language without documented opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The manifest description is written only in Chinese ("行业化 ROI 测算卡"), which indicates a fixed language choice without any visible user opt-in or documented locale constraint. This can violate language/locale policy expectations when the skill is otherwise not marked as region-specific.

Content

No source excerpt is available for this finding.