Back to skill

Security audit

TextRazor

Security checks for vulnerabilities and agentic risk

Overview

Review is warranted because fallback setup executes unverified downloaded code, and the linked CLI can change other agents’ installed skills without disclosure here.

Before use, install a reviewed, pinned CLI build and verify that automatic skill synchronization is disabled if you do not want other agent instructions changed. Submitted text passes through OOMOL to TextRazor. Keep explicit approval for deletions and overwrites. The remote installers and deployed connector implementation were not inspected.

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 does not interact with TextRazor. It executes an installer hosted on cli.oomol.com, with no demonstrated connection to the declared TextRazor functionality. This introduces an undeclared remote-code execution and installation capability. The downloaded script's contents and further effects cannot be determined from the supplied chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The supplied command performs a login operation but shows no TextRazor integration or data operations. Authentication could be a supporting implementation detail if tied to TextRazor, but no such connection is established in this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The installation fallback pipes a mutable remote script directly into Bash without version pinning, integrity verification, or a review step; the PowerShell alternative has the same issue. Compromise of the distribution endpoint could therefore execute arbitrary code with the agent process's permissions, exposing local files and credentials. Its conditional use for legitimate setup reduces exposure but does not remove this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

The workflow allows text-analysis payloads to be sent to third parties without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The execution workflow at lines L27–L31 sends action payloads through the OOMOL connector, including user text for the analysis actions listed at L41–L45. The safety section labels all untagged actions as reads that are safe to run directly, but does not warn that these actions transmit submitted content to TextRazor through OOMOL; read-only operations can still affect privacy.

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 81)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