Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md `node scripts/trading-analysis.js`
Security audit
Consortium AI Analysis
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed, read-only client for a trading-analysis API, with the main risk being that users must trust the external service and its API-key handling.
Install only if you trust Consortium AI with the TRADING_ANALYSIS_API_KEY and are comfortable receiving crypto trading signals from its API. Keep the key scoped to this service where possible, do not paste it into chats or logs, and remember the skill retrieves signals only; it does not execute trades.
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
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (11)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md `node scripts/trading-analysis.js`
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md `node scripts/trading-analysis.js`
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 96% confidence
- Finding
The skill explicitly requires an environment secret and repeatedly instructs making outbound network requests, but it does not declare any tool scope such as permissions or allowed-tools. That mismatch weakens platform-level guardrails by hiding the skill's need for secret access and external communication, increasing the chance an agent can exfiltrate the API key or call unreviewed endpoints without clear policy enforcement.
- Content
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 90% confidence
- Finding
This skill sends authenticated requests containing a secret API key to an external third-party service. External transmission is expected for the skill's purpose, but it still creates a real data-flow and trust-boundary risk because secrets are disclosed to a remote domain and any returned content is untrusted.
- Content
md **Backend API base URL:** `https://api.consortiumai.org` **Endpoint:** `GET https://api.consortiumai.org/api/trading-analysis` Returns the latest trading-only AI analysis (no lending). Optional filter by base token. ### Authentication
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
Example requests
http GET https://api.consortiumai.org/api/trading-analysis x-api-key: <TRADING_ANALYSIS_API_KEY>
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
Example requests
http GET https://api.consortiumai.org/api/trading-analysis x-api-key: <TRADING_ANALYSIS_API_KEY>
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
Example requests
http GET https://api.consortiumai.org/api/trading-analysis x-api-key: <TRADING_ANALYSIS_API_KEY>
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
Example requests
http GET https://api.consortiumai.org/api/trading-analysis x-api-key: <TRADING_ANALYSIS_API_KEY>
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
Example requests
http GET https://api.consortiumai.org/api/trading-analysis x-api-key: <TRADING_ANALYSIS_API_KEY>
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
Example requests
http GET https://api.consortiumai.org/api/trading-analysis x-api-key: <TRADING_ANALYSIS_API_KEY>
Static analysis
Detected: suspicious.env_credential_access
Environment variable access combined with network send.
Critical
- Code
- suspicious.env_credential_access
- Location
- scripts/trading-analysis.js:11