ClawHub
Back to skill

Security audit

Dovetail

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent Dovetail connector, but its fallback setup tells agents to run unverified remote installer scripts directly in a shell.

Use this skill only if you trust OOMOL as the intermediary for your Dovetail account. Do not let an agent run the installer commands automatically; install the oo CLI through a trusted, verified method and confirm any create or update payload before it runs.

A.I.G

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:61
Finding

Unverified Remote Installer Scripts Executed Directly by Shells

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 61–65
Vulnerability Type: Remote payload retrieval and execution
Risk Level: High

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 download mutable scripts from external URLs and immediately execute them with Bash or PowerShell. Neither command pins an audited release nor verifies a cryptographic signature or checksum before execution.

Consequently, the code that ultimately runs is controlled by the remote server at execution time and can differ from what was available when the Skill was reviewed. Compromise of the download server, publication pipeline, domain, or TLS trust path could result in arbitrary commands being supplied to the shell.

Installing the CLI is only a fallback when oo is unavailable and is not required for normal Dovetail connector operations. Automatic remote installation therefore exceeds the minimum privileges needed during an ordinary Skill invocation.

Attack Path

  1. The oo command is unavailable, causing the agent or user to follow the first-time setup instructions.
  2. An attacker compromises the installer endpoint, its deployment pipeline, or another component of the delivery trust chain.
  3. The attacker replaces the expected installer with a malicious shell or PowerShell payload.
  4. curl | bash or irm | iex executes the payload immediately, without prior inspection or integrity verification.
  5. The payload performs arbitrary actions with the privileges of the account running the command.

Impact Assessment

Successful exploitation provides arbitrary code execution under the invoking user's privileges. Depending on those privileges and the host configuration, the payload could read or modify accessible files, steal locally available credentials, alter tools or conf ...[truncated 296 chars]

Remediation
View remediation

Remediation Suggestions

  1. Remove both direct pipe-to-shell installation commands.
  2. Require explicit user approval before installing software; the Skill should not perform installation automatically.
  3. Pin the CLI to a specific audited release and download the installer or binary to a local file before execution.
  4. Publish and verify a cryptographic signature or trusted SHA-256 checksum over the downloaded artifact.
  5. Display the artifact source, version, destination, and requested permissions before installation.
  6. Prefer a trusted platform package manager or signed release package where available.
  7. Run installation with ordinary user privileges unless elevated privileges are demonstrably required.
  8. Keep installation separate from routine connector execution so normal Dovetail operations retain the declared Bash(oo *) least-privilege boundary.

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The skill instructs the agent to install software by piping a remotely fetched script directly into a shell, which is a classic supply-chain and remote code execution risk. If the install endpoint, transport, or upstream distribution is compromised, arbitrary code would execute immediately on the host running the skill.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says to use this skill for "ANY Dovetail request" and "Whenever a task involves Dovetail," which is an extremely broad activation condition. It does not provide scope boundaries, exclusions, or negative examples, so ordinary mentions of Dovetail could trigger the skill unintentionally.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.