Back to skill

Security audit

MoneybigA

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed stock-analysis skill that uses public web research and generates reports, with no evidence of credential access, persistence, hidden execution, or trading authority.

Install only if you want an assistant to perform web-based stock research and produce non-personalized trading-style signals. Review any buy/sell labels, stop-losses, or target prices critically, because the skill cannot guarantee data freshness or investment outcomes and does not replace licensed financial advice.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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
Findings (12)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
90% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.full.md (reported line 143)May include surrounding context.

卸载方法:

bash
rm -rf ~/.claude/skills/moneybigA

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
90% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 143)May include surrounding context.

卸载方法:

bash
rm -rf ~/.claude/skills/moneybigA

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
90% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.full.md (reported line 143)May include surrounding context.

卸载方法:

bash
rm -rf ~/.claude/skills/moneybigA

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
90% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 143)May include surrounding context.

卸载方法:

bash
rm -rf ~/.claude/skills/moneybigA

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger phrases are very broad and include common financial-language terms, which can cause the skill to activate unintentionally in unrelated conversations. Over-broad auto-invocation increases the chance that the skill performs web searches, generates persuasive financial guidance, or steers conversations when the user did not explicitly request this workflow.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest says outputs do not constitute investment advice and that the skill is for analysis only, yet later sections prescribe explicit trading actions such as '强烈买入/强烈卖出', stop-loss references, and target prices. That is a meaningful behavior-level mismatch because the documented operating instructions go beyond neutral analysis into actionable advice.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The '何时触发' section defines activation conditions so loosely that ordinary mentions of stocks, technical terms, or market topics may invoke the skill outside intended contexts. In an assistant environment, ambiguous routing can lead to unnecessary external lookups and unsolicited high-stakes financial recommendations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list is extremely broad and includes common finance phrases in both Chinese and English, which raises the chance of unintended or surprise invocation during ordinary discussion. Over-broad activation can cause the skill to run in contexts the user did not clearly intend, increasing exposure to downstream actions such as web retrieval, artifact generation, or persuasive financial recommendations.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.full.md (reported line 167)May include surrounding context.

验证安装

bash
ls ~/.claude/skills/moneybigA/
# 应看到:SKILL.md  _meta.json  package.json  .clawhub/

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 165)May include surrounding context.

验证安装

bash
ls ~/.claude/skills/moneybigA/
# 应看到:SKILL.md  _meta.json  package.json  .clawhub/

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

Line L087 states the skill does not backtest historical trading strategies and only analyzes current state, but later instructions rely on retrospective performance analysis such as '过去5年' PE percentiles and '历史预期兑现率'. While not strict strategy backtesting, the documentation creates a contradictory impression about use of historical analysis.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language instructions, examples, and operating guidance are predominantly Chinese, which can impose a language preference on users without explicit opt-in. The file does not state that the skill supports multiple languages or that Chinese is a required region-specific constraint.

Content

No source excerpt is available for this finding.