Back to skill

Security audit

httpSMS

Security checks for vulnerabilities and agentic risk

Overview

The httpSMS workflow is clearly described, but its setup fallback executes unverified downloaded code without a separate approval step.

Review and install a verified CLI release yourself before using this skill, and prevent the agent from running its automatic installer fallback. Check the CLI's bundled-skill synchronization settings. OOMOL will mediate access to your connected httpSMS account, including private messages. Keep confirmation enabled for sending and deletion. The remote installer and hosted connector implementation were not verified.

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 (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied command contains no httpSMS operation and instead runs an installer from cli.oomol.com. Nothing supplied establishes that this installer is a supporting dependency for httpSMS. The downloaded script's contents are unavailable, so its additional effects cannot be determined.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The supplied code performs only a CLI login and contains no identifiable httpSMS interaction. Authentication could be a supporting implementation detail if tied to httpSMS, but the supplied chunk establishes no such connection and instead has a materially different observable purpose.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping a remotely fetched installer directly into bash executes mutable external content without a pinned version, integrity verification, or review; the PowerShell alternative has the same weakness. Compromise of the script's distribution infrastructure could expose local credentials and files or enable persistent compromise, although exploitation requires the setup fallback to be reached and execution to be permitted.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

First-time setup executes downloaded installer scripts without a system-integrity warning or explicit approval.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The missing-CLI fallback directs installation by executing downloaded shell or PowerShell code without requiring explicit approval for local system changes. Although conditional and relevant to setup, this can expand an ordinary httpSMS request into arbitrary code execution with the agent's user privileges; the action-confirmation rules only explicitly cover httpSMS state changes.

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 84)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