Back to skill

Security audit

Textmagic

Security checks for vulnerabilities and agentic risk

Overview

The Textmagic workflow has appropriate approval controls, but its setup fallback can execute downloaded code without separate user approval.

Review and approve CLI installation separately, including changes to installed agent skills, and prefer a verified release. OOMOL mediates access to your Textmagic account; confirm SMS recipients, content, and charges before sending. Remote installer and service implementations were not verified; the artifact provides no evidence of 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
98% confidence
Finding

The supplied code installs external software rather than reading, creating, or updating Textmagic data. No visible code establishes that this installer is a supporting dependency for Textmagic. The remote script's contents are not supplied, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The curl-to-bash pipeline executes whatever script the HTTPS endpoint returns without pinning a version or verifying artifact integrity. Compromise of the distribution endpoint could therefore become arbitrary local code execution; this is the same underlying installer risk identified by SQP-2, not a separate exploit chain.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

Fallback setup executes downloaded installation scripts without warning about third-party code execution on the user's system.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback directs the agent to execute downloaded shell or PowerShell code without requiring informed approval or verifying the downloaded artifact. A compromised installer source could execute arbitrary code with the invoking user's privileges; limiting this behavior to missing-CLI errors reduces exposure but does not remove the risk.

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 82)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