T08 · Insecure Dependencies
Error
- Location
README.md:20- Finding
Unpinned External Packages and Repository Content Are Installed from Mutable Sources
- Content
View full analysis
- Remediation
View remediation
Security audit
Antalpha Ai Setup
Security checks for vulnerabilities and agentic risk
Overview
This skill connects an agent to a broad Web3 MCP service that includes real trading and transfer-capable tools, but the artifacts do not clearly document least-privilege setup, confirmations, or key-safety controls.
Review this carefully before installing. Use it only with credentials scoped to the minimum tools you need, prefer read-only access where possible, require out-of-band human approval for every trade, transfer, leverage, or order action, and avoid following mutable install commands unless you can pin and verify the exact package or repository revision.
Vulnerability Patterns
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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
Findings (2)
T05 · Unauthorized Access and Privilege Escalation
Error
- Location
SKILL.md:16- Finding
Remote MCP Integration Exposes High-Risk Financial Tools Without Documented Least-Privilege Controls
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 70% confidence
- Finding
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 70% confidence
- Finding
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The README instructs users to register an agent, obtain an
agent_idandapi_key, and then use Web3 tools capable of trading or other asset-affecting actions, but it provides no warning about key sensitivity, account scope, or real financial consequences. In a Web3 and trading context, this omission is more dangerous because users may paste credentials into broad-access clients or invoke transactional tools without understanding that funds, positions, or market actions could be affected.- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 70% confidence
- Finding
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The skill exposes numerous high-impact actions including swaps, leveraged perpetuals trading, CEX spot/futures orders, token transfers, and copy-trading features, but does not include prominent warnings, confirmation requirements, or guidance that these actions can move funds or open risky positions. In an agent context, this increases the chance of accidental or unsafe financial actions, especially if an LLM invokes tools based on ambiguous prompts or incomplete user intent.
- Content