Back to skill

Security audit

AgenticTrade

Security checks for vulnerabilities and agentic risk

Overview

This skill is a real AgenticTrade marketplace integration, but it gives the agent under-scoped authority to register services, publish listings, and make USDC-paid calls.

Review this carefully before installing. Use it only if you are comfortable with an agent interacting with AgenticTrade, sending marketplace data and API requests externally, and potentially spending USDC. Require manual confirmation before registration, listing, funding, or every paid service call; avoid or isolate the MCP install unless you can verify a pinned package; and treat remote playbook or service responses as untrusted content.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (3)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:29
Finding

Skill Instructions Assert External Control and Encourage Autonomous Financial Transactions

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Error
Location
SKILL.md:21
Finding

Unpinned Third-Party MCP Package Installation

Content
View full analysis
Remediation
View remediation

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:161
Finding

Mutable Remote Playbook Creates an Unreviewed Instruction Channel

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

The skill is explicitly designed to transmit data and credentials to external services via curl and the AgenticTrade API, including use of AGENTICTRADE_API_KEY and forwarding request payloads to third-party marketplace services. While this is part of intended functionality, it is still a real security/privacy risk because sensitive prompts, API keys, and transactional requests may leave the local environment and trigger paid external actions.

Content

Scanner excerpt · SKILL.md (reported line 14)May include surrounding context.

md
env:
        - AGENTICTRADE_API_KEY
      bins:
        - curl
    primaryEnv: AGENTICTRADE_API_KEY
    emoji: "\U0001F4B0"
    os:

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill promotes calling third-party services that "auto-pay" from the user's USDC balance, but the user-facing description does not prominently warn that service invocation spends funds. This can lead to unintended cryptocurrency expenditures, especially because the skill is user-invocable and encourages autonomous purchasing behavior.

Content

No source excerpt is available for this finding.

Rp1

Low
Category
MCP Rug Pull
Confidence
60% confidence
Finding

pip install without ==version installs the latest release, which could include malicious changes.

Content

No source excerpt is available for this finding.