Back to skill

Security audit

wttr.in

Security checks for vulnerabilities and agentic risk

Overview

The weather function is coherent, but missing-dependency setup immediately executes remote installers without verification or separate user approval.

Review and approve a pinned, verified oo installation separately before allowing automatic setup. Consider its OOMOL account and billing dependency and possible changes to other agents' installed skills. The bundled instructions were fully reviewed, but remote installer contents and live connector behavior remain unverified; no malicious intent was established.

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
99% confidence
Finding

The supplied command performs authentication rather than searching or reading wttr.in data. No connection between this login operation and wttr.in is shown, so it is not supported as an implementation detail of the declared purpose.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command does not access wttr.in or retrieve weather data. Instead, it executes an installer hosted at cli.oomol.com. Remote installer execution is a materially different, undeclared capability, and the supplied code provides no evidence that it is a supporting implementation detail for wttr.in access.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping the HTTPS response directly into bash executes mutable remote code with the agent process's privileges, without a pinned version or independent integrity check. A compromised installer server or release could access local files and credentials or modify the environment; the conditional setup context reduces exposure frequency but does not remove this risk.

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

Fallback setup instructs the agent to execute remote installation scripts without warning the user about system changes or downloaded-code execution.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

A missing CLI triggers instructions to download and immediately execute an installation script without first obtaining approval for host changes or verifying the downloaded code. Although this is a conditional dependency setup step rather than evidence of malicious intent, it can expose the agent's execution environment to arbitrary code if the installer delivery path is compromised.

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 70)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