ClawHub
Back to skill

Security audit

Polymarket Data

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent read-only prediction-market data skill, with wallet lookups that users should treat as privacy-sensitive.

Use this skill only if you are comfortable sending prediction-market searches, market IDs, wallet addresses, and your AISA API key to AIsa. Avoid querying third-party wallets unless you have a legitimate, authorized reason, and monitor API usage because the documentation states a per-query cost.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (19)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

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 · scripts/prediction_market_client.py (reported line 52)May include surrounding context.

python
class PredictionMarketClient:
    """Cross-Platform Prediction Market Data - AIsa API Client."""

    BASE_URL = "https://api.aisa.one/apis/v1"

    def __init__(self, api_key: Optional[str] = None):
        self.api_key = api_key or os.environ.get("AISA_API_KEY")

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 · skill.md (reported line 137)May include surrounding context.

md
class PredictionMarketClient:
    """Cross-Platform Prediction Market Data - AIsa API Client."""

    BASE_URL = "https://api.aisa.one/apis/v1"

    def __init__(self, api_key: Optional[str] = None):
        self.api_key = api_key or os.environ.get("AISA_API_KEY")

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 · skill.md (reported line 146)May include surrounding context.

md
class PredictionMarketClient:
    """Cross-Platform Prediction Market Data - AIsa API Client."""

    BASE_URL = "https://api.aisa.one/apis/v1"

    def __init__(self, api_key: Optional[str] = None):
        self.api_key = api_key or os.environ.get("AISA_API_KEY")

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 · skill.md (reported line 162)May include surrounding context.

md
class PredictionMarketClient:
    """Cross-Platform Prediction Market Data - AIsa API Client."""

    BASE_URL = "https://api.aisa.one/apis/v1"

    def __init__(self, api_key: Optional[str] = None):
        self.api_key = api_key or os.environ.get("AISA_API_KEY")

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 · skill.md (reported line 171)May include surrounding context.

md
class PredictionMarketClient:
    """Cross-Platform Prediction Market Data - AIsa API Client."""

    BASE_URL = "https://api.aisa.one/apis/v1"

    def __init__(self, api_key: Optional[str] = None):
        self.api_key = api_key or os.environ.get("AISA_API_KEY")

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 · skill.md (reported line 180)May include surrounding context.

md
class PredictionMarketClient:
    """Cross-Platform Prediction Market Data - AIsa API Client."""

    BASE_URL = "https://api.aisa.one/apis/v1"

    def __init__(self, api_key: Optional[str] = None):
        self.api_key = api_key or os.environ.get("AISA_API_KEY")

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 · skill.md (reported line 214)May include surrounding context.

md
class PredictionMarketClient:
    """Cross-Platform Prediction Market Data - AIsa API Client."""

    BASE_URL = "https://api.aisa.one/apis/v1"

    def __init__(self, api_key: Optional[str] = None):
        self.api_key = api_key or os.environ.get("AISA_API_KEY")

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 · skill.md (reported line 223)May include surrounding context.

md
class PredictionMarketClient:
    """Cross-Platform Prediction Market Data - AIsa API Client."""

    BASE_URL = "https://api.aisa.one/apis/v1"

    def __init__(self, api_key: Optional[str] = None):
        self.api_key = api_key or os.environ.get("AISA_API_KEY")

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 · skill.md (reported line 232)May include surrounding context.

md
class PredictionMarketClient:
    """Cross-Platform Prediction Market Data - AIsa API Client."""

    BASE_URL = "https://api.aisa.one/apis/v1"

    def __init__(self, api_key: Optional[str] = None):
        self.api_key = api_key or os.environ.get("AISA_API_KEY")

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 · skill.md (reported line 241)May include surrounding context.

md
class PredictionMarketClient:
    """Cross-Platform Prediction Market Data - AIsa API Client."""

    BASE_URL = "https://api.aisa.one/apis/v1"

    def __init__(self, api_key: Optional[str] = None):
        self.api_key = api_key or os.environ.get("AISA_API_KEY")

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 · skill.md (reported line 251)May include surrounding context.

md
class PredictionMarketClient:
    """Cross-Platform Prediction Market Data - AIsa API Client."""

    BASE_URL = "https://api.aisa.one/apis/v1"

    def __init__(self, api_key: Optional[str] = None):
        self.api_key = api_key or os.environ.get("AISA_API_KEY")

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 · skill.md (reported line 261)May include surrounding context.

md
class PredictionMarketClient:
    """Cross-Platform Prediction Market Data - AIsa API Client."""

    BASE_URL = "https://api.aisa.one/apis/v1"

    def __init__(self, api_key: Optional[str] = None):
        self.api_key = api_key or os.environ.get("AISA_API_KEY")

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This code sends user-supplied wallet identifiers and related filters to a remote service via HTTP requests, which can expose potentially sensitive financial-activity data to a third party. While network access is part of the client’s purpose, there is no confirmation prompt or explicit user-facing disclosure in the execution flow that wallet-related inputs will be transmitted externally.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly encourages tracking wallet positions and P&L by wallet address without warning that wallet addresses can reveal sensitive financial behavior and can often be linked to real identities through correlation. In an agent setting, this omission can normalize surveillance-style lookups of third-party wallets and lead to privacy-invasive use of on-chain financial data.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

This endpoint transmits a wallet address to a third-party API to retrieve user activity, which can expose trading behavior and financial history associated with that address. In combination with the skill's lack of privacy guidance, this creates a real privacy risk for users or third parties whose wallet addresses are queried without informed consent.

Content

Scanner excerpt · skill.md (reported line 154)May include surrounding context.

bash
# Fetch activity data for a specific user
curl -X GET "https://api.aisa.one/apis/v1/polymarket/activity?user={wallet_address}" \
  -H "Authorization: Bearer $AISA_API_KEY"

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

This endpoint sends a wallet address to a third-party service to retrieve all positions, revealing potentially sensitive holdings and exposure for that wallet. Because the documentation encourages this capability without a consent or privacy warning, it materially increases the risk of invasive profiling of individuals or entities.

Content

Scanner excerpt · skill.md (reported line 188)May include surrounding context.

bash
# Fetch all Polymarket positions for a proxy wallet address
curl -X GET "https://api.aisa.one/apis/v1/polymarket/positions/wallet/{wallet_address}" \
  -H "Authorization: Bearer $AISA_API_KEY"

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

Fetching wallet information by address sends potentially identifying financial metadata to an external provider and facilitates aggregation of on-chain identity information. In an autonomous-agent context, such lookups can occur at scale and without clear user awareness, making the privacy exposure more significant.

Content

Scanner excerpt · skill.md (reported line 196)May include surrounding context.

bash
# Fetch wallet information
curl -X GET "https://api.aisa.one/apis/v1/polymarket/wallet?eoa={wallet_address}" \
  -H "Authorization: Bearer $AISA_API_KEY"

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

This endpoint retrieves profit-and-loss for a wallet address, which is highly sensitive financial information even if derived from public-chain activity. Sending wallet identifiers to a third-party API for P&L analysis without warning or consent can enable financial surveillance, deanonymization, and profiling of trading success or losses.

Content

Scanner excerpt · skill.md (reported line 204)May include surrounding context.

bash
# Fetch realized profit and loss (PnL) for a specific wallet address
curl -X GET "https://api.aisa.one/apis/v1/polymarket/wallet/pnl/{wallet_address}?granularity=day" \
  -H "Authorization: Bearer $AISA_API_KEY"

Static analysis

No suspicious patterns detected.