Security audit

Agent Commercial Contract

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent with its legal and payment purpose, but it promotes autonomous contract signing and escrow/payment actions with weak safeguards and relies on unverifiable mutable installs.

Review carefully before installing. Use only a sandbox or staging environment first, pin and verify the npm package or Git commit, disable install scripts during inspection when possible, and require explicit human approval for signing contracts, depositing funds, releasing escrow, refunds, and dispute rulings.

A.I.G

Vulnerability Patterns

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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (2)

T08 · Insecure Dependencies

Warning

Location: skill.md:61
Finding: Unpinned External npm Package Installation in Skill Instructions
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: readme.md:53
Finding: Mutable npm and Git Dependency Installation Instructions
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The README explicitly demonstrates escrow deposit and release operations and promotes automated contract execution, but it does not warn that these actions can move funds or trigger irreversible legal/financial state changes. In an agent-oriented commerce framework, readers may treat example commands as safe defaults, increasing the risk of accidental payment release, unauthorized execution flows, or misuse in testing against real accounts.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill explicitly promotes autonomous negotiation, signing, execution, and enforcement of commercial agreements, along with escrow and payment handling, but does not prominently warn that these are legally and financially consequential actions. In an agent setting, this can normalize high-risk automation and lead users to deploy workflows that commit funds or enter binding agreements without sufficient human review or transactional safeguards.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The quick-start and CLI examples show how to register agents, create contracts with escrow, and enable milestone-based payment flows without any prominent caution that the operations may affect real money or create irreversible obligations. Because examples are often copied directly into production-like environments, this increases the likelihood of unsafe deployment by users who assume the workflow is low risk or purely demonstrative.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.