Back to skill

Security audit

Metered Data Fetch

Security checks for vulnerabilities and agentic risk

Overview

The skill is purpose-aligned but needs review because it can initiate account login, cache an authenticated session, and make paid network calls through a globally installed CLI.

Review before installing. Use this only if you are comfortable with SettleMesh account linking, cached authentication, metered paid calls, and sending requested data tasks through SettleMesh. Prefer a pinned or isolated CLI install, approve login deliberately, check quotes and ledger entries, and know how to clear the cached session before relying on it.

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 (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:36
Finding

Unpinned Global Installation of a Credential-Handling CLI

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The session guidance minimizes the security significance of browser-based login and cached sessions by framing it as 'never dead-stop on auth' and a one-time approval, without a prominent warning that this creates a persistent authenticated state for future paid API calls. In the context of a metered, network-connected skill, that makes unintended spending and silent reuse of credentials more likely, especially if the agent later performs additional calls under the cached session.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest description says to use the skill whenever the agent needs live web search, scraping, SEO/SERP, finance data, or an LLM, which is a very wide activation scope. It does not define exclusions or narrower trigger conditions, increasing the chance of unintended invocation for common requests involving search or model usage.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs the agent to run settlemesh whoami and, if unauthenticated, automatically invoke settlemesh login itself, opening a browser and caching a session, while explicitly telling the agent not to stop and ask the user to log in manually. This is dangerous because it initiates authentication and credential acquisition on the user's behalf without explicit consent, increases the chance of unintended account linking/session persistence, and normalizes autonomous auth flows for a paid networked service.

Content

No source excerpt is available for this finding.