Back to skill

Security audit

MarketSensor

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly performs disclosed MarketSensor API actions, but it also installs an overbroad prompt hook that can steer unrelated prompts toward using the service while handling an API key and account-changing actions.

Review this skill before installing if you do not want automatic prompt hooks. If installed, keep the MarketSensor API key limited to this service, avoid running the shell examples where command arguments may be logged or visible to local processes, and confirm watchlist removals or analysis requests because they can change your MarketSensor account state or consume quota.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (39)

Tp4

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding

声明描述的是一个较完整的股票/资产分析技能,包含多项能力:查自选、看报告、触发分析、查额度,并宣称支持多个市场。实际代码块的核心功能较窄:POST /api/open/analyze 触发分析,GET /api/open/analysis/status/{SYMBOL} 轮询状态,最后 GET /api/open/report/{REPORT_ID} 获取报告。因此它只覆盖了“触发分析”和“看报告”的一部分。代码没有任何自选列表查询、额度/配额查询相关接口调用,也没有体现针对美股、加密货币、A 股的市场区分或兼容处理。虽然代码行为与声明的部分能力一致,但声明明显比实际实现宽,存在能力层面的描述不准确。

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · scripts/check-quota.sh (reported line 16)May include surrounding context.

sh
AUTH="Authorization: Bearer $MARKETSENSOR_API_KEY"

echo "==> 查询账户额度..."
curl -s -H "$AUTH" "$BASE_URL/api/open/quota" | python3 -m json.tool 2>/dev/null || \
curl -s -H "$AUTH" "$BASE_URL/api/open/quota"

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill declares access to an environment secret and demonstrates shell-based network calls, but it does not define an explicit tool scope such as allowed-tools or permissions. This weakens containment and reviewability, because an agent executing the skill could use broader shell capabilities than are necessary while handling the API key.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description, instructions, examples, and operational guidance are all presented in Chinese, which effectively forces a specific language for users and downstream agents. Under the policy, language constraints should either be optional for the user or explicitly justified as region-specific.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

This POST request transmits user-selected symbols and an authorization bearer token to an external third-party service. External transmission is expected for an API-backed skill, but it remains security-relevant because the skill causes account-affecting actions on a remote system and handles a secret via shell commands.

Content

Scanner excerpt · SKILL.md (reported line 71)May include surrounding context.

当用户说「帮我关注一下 AAPL」或「把特斯拉加到自选」时:

bash
curl -s -X POST -H "Authorization: Bearer $MARKETSENSOR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"symbol": "AAPL"}' \
  https://api.marketsensor.ai/api/open/watchlist

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

This endpoint removes symbols from a remote watchlist while sending the bearer token to an external service. Because it performs a state-changing action tied to the user's account, accidental or unauthorized execution could alter user data even though the destination appears aligned with the skill's purpose.

Content

Scanner excerpt · SKILL.md (reported line 90)May include surrounding context.

当用户说「不关注 META 了」或「把苹果从自选里删掉」时:

bash
curl -s -X POST -H "Authorization: Bearer $MARKETSENSOR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"symbol": "META"}' \
  https://api.marketsensor.ai/api/open/watchlist/remove

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

This request sends a bearer token and stock symbol to a third-party analysis API to initiate processing. The behavior matches the stated function, but it still introduces external data transfer, quota consumption, and possible secret exposure risks if implemented via unrestricted shell commands.

Content

Scanner excerpt · SKILL.md (reported line 119)May include surrounding context.

当用户说「帮我分析一下 TSLA」或「看看英伟达现在怎么样」时,如果没有现成报告,需要触发生成:

bash
curl -s -X POST -H "Authorization: Bearer $MARKETSENSOR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"symbol": "TSLA"}' \
  https://api.marketsensor.ai/api/open/analyze

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The document content is written in Chinese ('用户反馈的功能请求。') and the example request fields are also Chinese, with no indication that language selection is optional or that the skill is specifically limited to a Chinese-speaking context. This creates a natural-language locale policy concern because it implicitly enforces a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The hook triggers on broad conditions like any mention of stock symbols or analysis-related keywords at UserPromptSubmit time, which can cause unsolicited promotion of the skill in many unrelated conversations. This creates prompt-routing/manipulation risk by steering users toward the skill without clear user intent, and may expose financial-analysis functionality in contexts where it was not requested.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The natural-language instruction is written as a mandatory behavior in Chinese and provides no indication that the user can choose another language. This creates a language/locale policy concern because the skill appears to enforce a specific language without opt-in or documented regional justification.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · references/examples.md (reported line 9)May include surrounding context.

bash
# 1. 先查状态
curl -s -H "Authorization: Bearer $MARKETSENSOR_API_KEY" \
  https://api.marketsensor.ai/api/open/analysis/status/NVDA

# 返回: { "status": "none" }

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 54)May include surrounding context.

bash
# 1. 先查状态
curl -s -H "Authorization: Bearer $MARKETSENSOR_API_KEY" \
  https://api.marketsensor.ai/api/open/analysis/status/NVDA

# 返回: { "status": "none" }

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 74)May include surrounding context.

bash
# 1. 先查状态
curl -s -H "Authorization: Bearer $MARKETSENSOR_API_KEY" \
  https://api.marketsensor.ai/api/open/analysis/status/NVDA

# 返回: { "status": "none" }

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 93)May include surrounding context.

bash
# 1. 先查状态
curl -s -H "Authorization: Bearer $MARKETSENSOR_API_KEY" \
  https://api.marketsensor.ai/api/open/analysis/status/NVDA

# 返回: { "status": "none" }

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 102)May include surrounding context.

bash
# 1. 先查状态
curl -s -H "Authorization: Bearer $MARKETSENSOR_API_KEY" \
  https://api.marketsensor.ai/api/open/analysis/status/NVDA

# 返回: { "status": "none" }

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 122)May include surrounding context.

bash
# 1. 先查状态
curl -s -H "Authorization: Bearer $MARKETSENSOR_API_KEY" \
  https://api.marketsensor.ai/api/open/analysis/status/NVDA

# 返回: { "status": "none" }

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 153)May include surrounding context.

bash
# 1. 先查状态
curl -s -H "Authorization: Bearer $MARKETSENSOR_API_KEY" \
  https://api.marketsensor.ai/api/open/analysis/status/NVDA

# 返回: { "status": "none" }

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.

bash
# 1. 先查状态
curl -s -H "Authorization: Bearer $MARKETSENSOR_API_KEY" \
  https://api.marketsensor.ai/api/open/analysis/status/NVDA

# 返回: { "status": "none" }

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 174)May include surrounding context.

bash
# 1. 先查状态
curl -s -H "Authorization: Bearer $MARKETSENSOR_API_KEY" \
  https://api.marketsensor.ai/api/open/analysis/status/NVDA

# 返回: { "status": "none" }

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 · references/examples.md (reported line 10)May include surrounding context.

bash
# 1. 先查状态
curl -s -H "Authorization: Bearer $MARKETSENSOR_API_KEY" \
  https://api.marketsensor.ai/api/open/analysis/status/NVDA

# 返回: { "status": "none" }

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 · references/examples.md (reported line 18)May include surrounding context.

bash
# 1. 先查状态
curl -s -H "Authorization: Bearer $MARKETSENSOR_API_KEY" \
  https://api.marketsensor.ai/api/open/analysis/status/NVDA

# 返回: { "status": "none" }

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 · references/examples.md (reported line 25)May include surrounding context.

bash
# 1. 先查状态
curl -s -H "Authorization: Bearer $MARKETSENSOR_API_KEY" \
  https://api.marketsensor.ai/api/open/analysis/status/NVDA

# 返回: { "status": "none" }

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 · references/examples.md (reported line 31)May include surrounding context.

bash
# 1. 先查状态
curl -s -H "Authorization: Bearer $MARKETSENSOR_API_KEY" \
  https://api.marketsensor.ai/api/open/analysis/status/NVDA

# 返回: { "status": "none" }

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 · references/examples.md (reported line 39)May include surrounding context.

bash
# 1. 先查状态
curl -s -H "Authorization: Bearer $MARKETSENSOR_API_KEY" \
  https://api.marketsensor.ai/api/open/analysis/status/NVDA

# 返回: { "status": "none" }

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 · references/examples.md (reported line 73)May include surrounding context.

bash
# 1. 先查状态
curl -s -H "Authorization: Bearer $MARKETSENSOR_API_KEY" \
  https://api.marketsensor.ai/api/open/analysis/status/NVDA

# 返回: { "status": "none" }