Back to skill

Security audit

2Chat

Security checks for vulnerabilities and agentic risk

Overview

The 2Chat integration is clearly scoped, but its setup directs the agent to run downloaded software without a separate approval step.

Review and install the CLI separately before using this skill, and require approval for future software installation. Check its automatic skill synchronization settings and understand that OOMOL mediates access to your connected 2Chat account. Account writes have explicit confirmation safeguards, but the downloaded installers and runtime were not audited.

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
96% confidence
Finding

The supplied command performs no visible 2Chat operation. Instead, it fetches and executes an Oomol installation script. Nothing in the supplied content establishes this as a supporting dependency for 2Chat, making the observed behavior materially different from the declared purpose. The remote script's contents and further effects cannot be determined from this chunk.

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-delivered code with the invoking user's privileges, without inspecting it or verifying a pinned artifact. HTTPS and the legitimate dependency context do not protect against compromise of the distribution endpoint or installer supply chain; the PowerShell example has the same execution pattern.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

First-time setup instructs the agent to execute downloaded installer scripts without warning the user about system changes.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

When the CLI is absent, the skill directs installation without requiring disclosure of local system changes or explicit user approval. A request to operate on 2Chat data does not necessarily authorize installing software on the host; limiting installation to a missing-command error reduces its frequency but does not establish consent.

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 80)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