Back to skill

Security audit

Us Treasury Radar

Security checks for vulnerabilities and agentic risk

Overview

This skill does not show malicious behavior, but its financial report can present hard-coded or estimated market data as a live monitoring signal.

Review before installing if you expect authoritative or current financial data. Treat the output as an indicative report only, verify Treasury/TIC figures independently before making investment decisions, and be aware that the skill outputs Chinese text and may trigger on broad finance-related phrases.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document is entirely written in Chinese and presents the skill's output example and usage only in Chinese, which indicates a fixed language behavior. Under the policy, language constraints should either be optional for the user or clearly justified as region-specific; neither is stated here.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger list contains broad and weakly scoped phrases such as '美债分析', 'US Treasury analysis', and especially unrelated or overloaded terms like '浑水报告', 'Muddy Waters', and '戴维期双杀' without exclusions or context boundaries. This can cause accidental or adversarial invocation in unrelated financial, research, or news contexts, leading the agent to produce specialized market analysis when the user did not clearly request this skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This code file contains user-facing natural language in the module docstring entirely in Chinese, including the title and data-source description. Under the policy rule, forcing a specific language without offering the user a choice or documenting a justified locale constraint is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The printed report headings, labels, and notes are all emitted in Chinese, which imposes a specific language on users. The file does not offer any language selection or explain a justified region-specific requirement, so this conflicts with the language/locale policy.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The script presents country holdings as if they are based on TIC monthly reports, but the values are hard-coded estimates rather than fetched or validated from TIC data. This is dangerous because users may treat the output as authoritative, timely financial data and make decisions based on misleading provenance and stale numbers.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The skill is written entirely in Chinese and presents Chinese-only naming and output examples without indicating language negotiation or fallback behavior. While not directly a code-execution issue, this can cause misuse, misunderstanding of financial outputs, or degraded safety if users receive analysis in a language they did not request or cannot accurately interpret.

Content

No source excerpt is available for this finding.