Back to skill

Security audit

Appstle Subscriptions

Security checks for vulnerabilities and agentic risk

Overview

The Appstle data-reading features fit the stated purpose, but setup can execute unverified downloaded code and introduce broader agent changes without clear approval.

Review the setup before installing. Install a reviewed CLI version yourself, control whether it installs or synchronizes other agent skills, and connect only the Appstle account needed. OOMOL mediates access to customer data. The concern is setup authority and under-disclosed changes; the inspected skill does not establish malicious intent.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code performs remote software installation, not Appstle data searching or reading. Nothing in the chunk connects this installer to the declared Appstle functionality, so it cannot be treated as merely a demonstrated supporting implementation detail. The downloaded script's further behavior is not visible.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an HTTPS response directly into bash executes mutable remote code without independently verifying its integrity or reviewing it first. A compromised installation endpoint or release pipeline could execute attacker-controlled commands with the invoking user's privileges; the legitimate dependency context and missing-CLI condition narrow exposure but do not remove this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

Fallback setup executes downloaded scripts without warning about remote code execution or system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The missing-CLI fallback directs installation through remotely fetched shell or PowerShell code without requiring informed approval or explaining that installation executes code and changes the local environment. Its conditional placement and the declared Bash(oo *) tool restriction reduce immediate execution exposure, but neither makes the documented installation procedure safe if a user or more broadly privileged agent follows it.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 79)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources