Marketpulse

• Outcome: Pass
• Latest audit: May 29, 2026 · 8:41 PM UTC
• Version: 1.0.2

Overview

Marketpulse is a coherent market-data skill that uses a disclosed AIsa API key to fetch financial data from AIsa, with no evidence of hidden behavior or unrelated access.

Install only if you trust AIsa and are comfortable letting the agent use AISA_API_KEY to send financial queries, tickers, screening filters, and similar research parameters to api.aisa.one. Monitor usage because requests may cost credits, and avoid using sensitive portfolio or client-specific screens unless that external transmission is acceptable.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (26)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 87% confidence
• Finding: The skill declares required binaries and environment variables and clearly performs outbound network requests, but it does not declare corresponding permissions. That mismatch can prevent users and harnesses from accurately understanding the skill's capabilities, leading to unintended secret access and external data transmission.

Vague Triggers

Medium

• Confidence: 81% confidence
• Finding: The description is broad enough to trigger on generic stock, market, watchlist, or portfolio requests, increasing the chance this skill is invoked when the user did not specifically intend third-party API usage. Over-broad routing can expose user prompts and requested symbols to an external service unnecessarily.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The markdown repeatedly instructs the agent to send requests and an API bearer token to a third-party financial service, but it does not provide an explicit user-facing warning about external transmission. Users may not realize their queries, watchlists, or portfolio-related requests are being sent off-platform to AIsa.

External Transmission

Medium

• Category: Data Exfiltration

Content

```bash
# Historical price data (daily)
curl "https://api.aisa.one/apis/v1/financial/prices?ticker=AAPL&interval=day&interval_multiplier=1&start_date=2025-01-01&end_date=2025-12-31" \
  -H "Authorization: Bearer $AISA_API_KEY"

# Weekly price data

• Confidence: 93% confidence
• Finding: This example performs an authenticated outbound request to a third-party endpoint using the user's API key. In the skill context, transmitting ticker queries and related request parameters externally is expected functionality, but it is still a real data egress path that can disclose user intent and consume paid API credits.

External Transmission

Medium

• Category: Data Exfiltration

Content

```bash
# Historical price data (daily)
curl "https://api.aisa.one/apis/v1/financial/prices?ticker=AAPL&interval=day&interval_multiplier=1&start_date=2025-01-01&end_date=2025-12-31" \
  -H "Authorization: Bearer $AISA_API_KEY"

# Weekly price data

• Confidence: 93% confidence
• Finding: This example performs an authenticated outbound request to a third-party endpoint using the user's API key. In the skill context, transmitting ticker queries and related request parameters externally is expected functionality, but it is still a real data egress path that can disclose user intent and consume paid API credits.

External Transmission

Medium

• Category: Data Exfiltration

Content

-H "Authorization: Bearer $AISA_API_KEY"

# Weekly price data
curl "https://api.aisa.one/apis/v1/financial/prices?ticker=AAPL&interval=week&interval_multiplier=1&start_date=2025-01-01&end_date=2025-12-31" \
  -H "Authorization: Bearer $AISA_API_KEY"

# Minute-level data (intraday)

• Confidence: 91% confidence
• Finding: This is another authenticated outbound call to the AIsa API. It is expected for a market-data skill, but it still exposes request contents externally and can incur API-key-backed usage without an explicit warning or consent flow.

External Transmission

Medium

• Category: Data Exfiltration

Content

-H "Authorization: Bearer $AISA_API_KEY"

# Minute-level data (intraday)
curl "https://api.aisa.one/apis/v1/financial/prices?ticker=AAPL&interval=minute&interval_multiplier=5&start_date=2025-01-15&end_date=2025-01-15" \
  -H "Authorization: Bearer $AISA_API_KEY"
```

• Confidence: 91% confidence
• Finding: The intraday price example transmits query details to a third-party service using bearer authentication. As with other endpoints, this is legitimate functionality but still represents external egress and paid-key usage that should be clearly disclosed and permissioned.

External Transmission

Medium

• Category: Data Exfiltration

Content

```bash
# Get news by ticker
curl "https://api.aisa.one/apis/v1/financial/news?ticker=AAPL&limit=10" \
  -H "Authorization: Bearer $AISA_API_KEY"
```

• Confidence: 91% confidence
• Finding: The company-news example sends ticker queries to a third-party API with authentication. Even though the payload is not highly sensitive by itself, user research interests and trading intent can be inferred from such requests.

External Transmission

Medium

• Category: Data Exfiltration

Content

```bash
# All financial statements (requires period)
curl "https://api.aisa.one/apis/v1/financial/financials?ticker=AAPL&period=annual" \
  -H "Authorization: Bearer $AISA_API_KEY"

# Income statements

• Confidence: 91% confidence
• Finding: This financial-statements request sends a user-selected ticker and authenticated request to an external service. The context makes the transmission expected, but it remains a real egress path and billing vector that should be transparently disclosed.

External Transmission

Medium

• Category: Data Exfiltration

Content

-H "Authorization: Bearer $AISA_API_KEY"

# Income statements
curl "https://api.aisa.one/apis/v1/financial/financials/income-statements?ticker=AAPL&period=annual" \
  -H "Authorization: Bearer $AISA_API_KEY"

# Balance sheets

• Confidence: 91% confidence
• Finding: The income-statements example is another authenticated third-party request. Repeated examples indicate the skill's core behavior is external retrieval, so users need explicit awareness that financial lookups leave the local environment.

External Transmission

Medium

• Category: Data Exfiltration

Content

-H "Authorization: Bearer $AISA_API_KEY"

# Balance sheets
curl "https://api.aisa.one/apis/v1/financial/financials/balance-sheets?ticker=AAPL&period=annual" \
  -H "Authorization: Bearer $AISA_API_KEY"

# Cash flow statements

• Confidence: 91% confidence
• Finding: This balance-sheet request transmits a ticker and period externally using the API key. The risk is not malicious exfiltration, but undisclosed external processing and consumption of a bearer-authenticated paid service.

External Transmission

Medium

• Category: Data Exfiltration

Content

-H "Authorization: Bearer $AISA_API_KEY"

# Cash flow statements
curl "https://api.aisa.one/apis/v1/financial/financials/cash-flow-statements?ticker=AAPL&period=annual" \
  -H "Authorization: Bearer $AISA_API_KEY"
```

• Confidence: 91% confidence
• Finding: The cash-flow-statement example is a further outbound API call with bearer authentication. In this skill, such transmissions are normal, but they still constitute data egress and should be treated as a privacy and cost-sensitive operation.

External Transmission

Medium

• Category: Data Exfiltration

Content

```bash
# Break down revenue by business segment and geography
curl "https://api.aisa.one/apis/v1/financial/financials/segmented-revenues?ticker=AAPL&period=annual" \
  -H "Authorization: Bearer $AISA_API_KEY"
```

• Confidence: 91% confidence
• Finding: The segmented-revenues example sends user-selected company data requests to a third-party service. This can reveal research focus or investment interest and uses a secret-backed external API without an explicit warning in the skill text.

External Transmission

Medium

• Category: Data Exfiltration

Content

```bash
# Real-time financial metrics snapshot
curl "https://api.aisa.one/apis/v1/financial/financial-metrics/snapshot?ticker=AAPL" \
  -H "Authorization: Bearer $AISA_API_KEY"

# Historical financial metrics (period required)

• Confidence: 91% confidence
• Finding: This metrics snapshot request is an authenticated outbound call. Although common for a data skill, it still sends user query context outside the harness and should be consented to rather than implied.

External Transmission

Medium

• Category: Data Exfiltration

Content

-H "Authorization: Bearer $AISA_API_KEY"

# Historical financial metrics (period required)
curl "https://api.aisa.one/apis/v1/financial/financial-metrics?ticker=AAPL&period=annual" \
  -H "Authorization: Bearer $AISA_API_KEY"
```

• Confidence: 91% confidence
• Finding: The historical metrics example continues the same external transmission pattern. The context reduces suspicion of malice, but not the operational risk of undisclosed data egress and API key usage.

External Transmission

Medium

• Category: Data Exfiltration

Content

```bash
# Earnings per share estimates
curl "https://api.aisa.one/apis/v1/financial/analyst-estimates?ticker=AAPL&period=annual" \
  -H "Authorization: Bearer $AISA_API_KEY"
```

• Confidence: 91% confidence
• Finding: This analyst-estimates request sends the ticker and period to a third-party provider with bearer authentication. Such calls can reveal the user's active research targets and should not occur without clear disclosure.

External Transmission

Medium

• Category: Data Exfiltration

Content

```bash
# Get earnings press releases
curl "https://api.aisa.one/apis/v1/financial/earnings/press-releases?ticker=NVDA" \
  -H "Authorization: Bearer $AISA_API_KEY"
```

• Confidence: 91% confidence
• Finding: The earnings-press-releases example is another authenticated outbound request. Even if the data itself is public, the act of querying may expose user trading interest and consume API credits.

External Transmission

Medium

• Category: Data Exfiltration

Content

```bash
# Get insider trades
curl "https://api.aisa.one/apis/v1/financial/insider-trades?ticker=AAPL" \
  -H "Authorization: Bearer $AISA_API_KEY"
```

• Confidence: 92% confidence
• Finding: Insider-trade queries can be especially revealing of user investment strategies or due-diligence activity when sent to a third party. This is expected functionality but still merits clear notice and access controls.

External Transmission

Medium

• Category: Data Exfiltration

Content

```bash
# Get institutional ownership (by ticker OR investor)
curl "https://api.aisa.one/apis/v1/financial/institutional-ownership?ticker=AAPL" \
  -H "Authorization: Bearer $AISA_API_KEY"
```

• Confidence: 92% confidence
• Finding: Institutional-ownership lookups transmit ticker or investor-related parameters externally using the API key. Depending on use, this may expose sensitive research patterns or client-related interests to the provider.

External Transmission

Medium

• Category: Data Exfiltration

Content

```bash
# Get SEC filings
curl "https://api.aisa.one/apis/v1/financial/filings?ticker=AAPL" \
  -H "Authorization: Bearer $AISA_API_KEY"

# Get SEC filing items (requires filing type and year)

• Confidence: 91% confidence
• Finding: SEC-filings retrieval sends selected company information to a third-party API. The context makes this a normal feature, but it remains a real external transfer and should be covered by permissioning and privacy disclosures.

External Transmission

Medium

• Category: Data Exfiltration

Content

-H "Authorization: Bearer $AISA_API_KEY"

# Get SEC filing items (requires filing type and year)
curl "https://api.aisa.one/apis/v1/financial/filings/items?ticker=AAPL&filing_type=10-K&year=2024" \
  -H "Authorization: Bearer $AISA_API_KEY"
```

• Confidence: 91% confidence
• Finding: The filing-items example adds more specific query parameters such as filing type and year to an authenticated external request. This increases the granularity of information about what the user is researching and should be disclosed.

External Transmission

Medium

• Category: Data Exfiltration

Content

```bash
# Get company facts (by ticker or CIK)
curl "https://api.aisa.one/apis/v1/financial/company/facts?ticker=AAPL" \
  -H "Authorization: Bearer $AISA_API_KEY"
```

• Confidence: 91% confidence
• Finding: Company-facts retrieval is another bearer-authenticated request to a third-party service. Even where the requested facts are public, the user's selected targets and query timing may still be sensitive.

External Transmission

Medium

• Category: Data Exfiltration

Content

```bash
# Screen for stocks matching criteria
curl -X POST "https://api.aisa.one/apis/v1/financial/financials/search/screener" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"filters":{"pe_ratio":{"max":15},"revenue_growth":{"min":0.2}}}'

• Confidence: 93% confidence
• Finding: The screener example sends structured financial filters in a POST body to a third-party service. Those filters can reveal proprietary trading criteria or research strategy, making this more sensitive than simple public-data lookups.

External Transmission

Medium

• Category: Data Exfiltration

Content

```bash
# Search specific financial line items across tickers
curl -X POST "https://api.aisa.one/apis/v1/financial/financials/search/line-items" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"tickers":["AAPL","MSFT"],"line_items":["revenue","net_income"],"period":"annual"}'

• Confidence: 94% confidence
• Finding: This line-items search sends a list of tickers, requested metrics, and period in a POST body to a third-party API. That can reveal a user's analytical framework, targets, and portfolio-research methodology, making external disclosure more consequential.

External Transmission

Medium

• Category: Data Exfiltration

Content

```bash
# Current interest rates
curl "https://api.aisa.one/apis/v1/financial/macro/interest-rates/snapshot" \
  -H "Authorization: Bearer $AISA_API_KEY"

# Historical interest rates

• Confidence: 89% confidence
• Finding: The interest-rates snapshot request is an external authenticated call, but it is less sensitive than portfolio- or ticker-specific lookups because it does not directly encode a user's holdings or screening strategy. It is still an outbound network action that should be declared and disclosed.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.