Security audit

SettleMesh

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for SettleMesh deployment and billing, but it delegates high-impact paid and credentialed operations to mutable remote instructions and unpinned package execution.

Review carefully before installing. Use a pinned, reviewed SettleMesh package version if possible, avoid exposing broad environment variables to the MCP process, use narrowly scoped credentials, and require explicit confirmation with clear cost and destination details before deployment, billing, publishing, or destructive actions.

A.I.G

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 (2)

T08 · Insecure Dependencies

Error

Location: SKILL.md:12
Finding: Unpinned Third-Party Package Installation and Execution
Content: View full analysis
Remediation: View remediation

T01 · Skill Instruction Hijacking

Warning

Location: SKILL.md:14
Finding: Mutable Remote Agent Contract Can Introduce Unreviewed Instructions
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
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 (2)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The skill's activation criteria are broad enough to match many common requests about shipping apps, auth, databases, billing, or AI/API development. That increases the chance the agent will invoke this skill in loosely related contexts, exposing users to deployment, authentication, payment, and paid-tool workflows they did not explicitly request, which is especially risky because the skill can trigger billed and externally visible actions.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 93% confidence
Finding: The skill instructs users to run npx -y settlemesh, which resolves and executes the latest package version at runtime without pinning. In a security-sensitive agent skill, this creates a supply-chain risk: a compromised publisher account, malicious new release, or dependency hijack could cause arbitrary code execution on the host when the MCP server is launched.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.