Grafana

• Outcome: Review
• Latest audit: Sep 16, 2026 · 9:17 AM UTC
• Version: 1.0.4

Overview

The skill is coherent Grafana connector guidance, but its setup instructions tell the agent/user to run unverified remote installer scripts directly in a shell.

Review before installing. Use safer official installation methods for the oo CLI where possible, and do not let an agent run the remote installer automatically. Explicitly approve any Grafana write or delete payload before it runs.

A.I.G

Vulnerability Patterns

• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

Findings (1)

T03 · Remote Payload Retrieval and Execution

Error

• Location: SKILL.md:73

Finding

Unverified Remote Installer Downloaded and Executed Directly

Content

View full analysis

Vulnerability Details

File Location: SKILL.md, lines 73–77
Vulnerability Type: Remote payload retrieval and execution
Risk Level: High

Vulnerable Code

bash

curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux

powershell

irm https://cli.oomol.com/install.ps1 | iex           # Windows PowerShell

Technical Analysis

The first-time setup instructions retrieve mutable scripts from cli.oomol.com and immediately pass their contents to a command interpreter. The downloaded scripts are not included in the audited project, and the instructions provide no version pinning, cryptographic signature verification, checksum validation, or opportunity to inspect the files before execution.

Consequently, the code ultimately executed can change after this Skill has been reviewed. Compromise of the distribution server, its publishing process, or the delivered installer could cause arbitrary commands to run in the Agent or user's security context.

Installing the required CLI may be legitimate, but executing an unverified remote script directly is not the minimum privilege or safest mechanism necessary to provide that functionality.

Attack Path

1. The oo executable is unavailable, causing the Agent or user to follow the first-time setup instructions.
2. The Agent executes the documented curl | bash or irm | iex command.
3. The command retrieves the current installer from the external server without verifying a pinned version, signature, or checksum.
4. The shell immediately interprets the response as executable code.
5. If the remote installer or its distribution path has been compromised, attacker-controlled commands execute with the invoking account's privileges.

Impact Assessment

A malicious installer could perform any operation available to the invoking account, including:

• Reading or modifying user-accessible files.
• Accessing credentials, environme ...[truncated 750 chars]

Remediation

View remediation

Remediation Suggestions

1. Remove the direct curl | bash and irm | iex installation commands.
2. Prefer an authenticated operating-system package repository or another package manager that supports signed, versioned releases.
3. If script-based installation remains necessary:
   • Download a specific, immutable installer version to a local file.
   • Publish and verify a cryptographic signature using a trusted public key.
   • At minimum, verify a pinned cryptographic checksum obtained through an independently authenticated channel.
   • Inspect the downloaded file before execution.
   • Require explicit user approval before running it.
4. Never recommend executing the installer with administrator or root privileges unless individual operations have been documented as requiring those privileges.
5. Pin the CLI version used by the Skill and document a controlled update process so that installation behavior cannot change silently after review.
6. Keep installation separate from normal Grafana actions; failure due to a missing CLI should produce instructions rather than automatically executing remote installation code.

SkillSpector

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

External Script Fetching

High

• Category: Supply Chain
• Confidence: 98% confidence

Finding

The skill recommends installing software via curl -fsSL https://cli.oomol.com/install.sh | bash, which pipes a remotely fetched script directly into a shell. If the remote server, CDN, DNS, TLS trust chain, or distribution path is compromised, arbitrary code would execute immediately on the user's machine with the user's privileges.

Content

Scanner excerpt · SKILL.md (reported line 73)May include surrounding context.

• oo: command not found — install the oo CLI (other platforms: https://cli.oomol.com/install-guide.md):

  bash

  curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
  

  powershell

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The description says to use this skill for "ANY Grafana request" and "Whenever a task involves Grafana," which is an extremely broad activation condition. It does not define boundaries, exclusions, or negative examples, so ordinary Grafana-related discussion could be interpreted as a trigger to invoke the skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.