Back to skill

Security audit

Grafana Cloud

Security checks for vulnerabilities and agentic risk

Overview

The Grafana read operations fit the stated purpose, but setup can automatically execute an unverified remote installer.

Review and install a verified CLI version yourself before use, and retain control over additional agent skills it installs or synchronizes. Use a read-only Grafana credential and consider whether you trust OOMOL to handle the connection. The external installers and hosted connector were not verified, so this review does not establish their safety.

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
99% confidence
Finding

The supplied command performs remote script execution for an apparent CLI installation, not Grafana Cloud searches or reads. Nothing in the chunk establishes this installation as a supporting dependency for the declared purpose. The downloaded script is not provided, so its additional behavior cannot be assessed.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an unpinned remote script directly into bash gives its publisher, or an attacker controlling its delivery infrastructure, code execution on the agent's host. HTTPS protects transport but does not establish artifact integrity against a compromised publisher; this is the same underlying installer vulnerability identified by SQP-2, not a separate attack chain.

Content

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

First-time setup instructs immediate execution of downloaded installer scripts without a system-integrity warning.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The setup instructions execute downloaded shell and PowerShell scripts immediately, without an integrity check, pinned artifact, or explicit installation approval. A compromised distribution endpoint could execute arbitrary code with the invoking user's privileges; limiting this to a missing-CLI error reduces exposure but does not make execution safe.

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