Back to skill

Security audit

MetatextAI

Security checks for vulnerabilities and agentic risk

Overview

The MetatextAI integration is coherent, but its setup and CLI defaults can change your agent environment without clearly explaining those effects.

Review the CLI installation separately and prefer a verified release. Before running this skill, consider disabling the CLI's startup skill synchronization using its documented OO_SKILLS_SYNC_DISABLED setting. Submit only transcripts you authorize OOMOL and MetatextAI to process, and review policy changes and test scans before approval. The remote installers and deployed CLI binary 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 code performs remote installer execution rather than any visible MetatextAI data operation. Nothing in the description or code establishes this installation as a supporting dependency for MetatextAI. The downloaded script's contents are not supplied, so its further effects cannot be determined.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
82% confidence
Finding

The supplied chunk only initiates a CLI login and contains no MetatextAI-specific operations or configuration. Authentication could support a legitimate integration, but nothing here establishes that oo authenticates to MetatextAI. As supplied, the code's primary behavior does not substantiate the declared purpose.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a remotely fetched installer directly into Bash executes mutable network-supplied code without integrity verification or an inspection step; the PowerShell alternative has the same weakness. A compromised distribution endpoint could run arbitrary code with the invoking user's permissions, exposing local files and credentials, although the missing-CLI prerequisite limits when this path is reached.

Content

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

The execution workflow lacks a privacy warning for transmitting chat transcripts to external services.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The workflow instructs the agent to submit action payloads through the OOMOL connector, including chat transcripts when executing evaluate (L41). Although the file identifies the services involved, it does not warn that transcript contents may contain sensitive information and will be transmitted externally; L47 further treats untagged actions as safe to run directly.

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