ClawHub
Back to skill

Security audit

Benzinga

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a read-only Benzinga connector, but its setup instructions include unverified remote installer commands that can execute code on the user's machine.

Install only if you are comfortable using OOMOL as the broker for Benzinga access and avoid running the pasted installer commands blindly. Prefer installing the oo CLI from reviewed official instructions with verification, then sign in and connect Benzinga intentionally before using the skill.

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:57
Finding

Unverified Remote Installer Scripts Executed Directly by Shells

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 57–63
Vulnerability Type: T03: Remote Payload Retrieval and Execution
Risk Level: Critical

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 scripts from cli.oomol.com and execute the HTTP responses immediately using Bash or PowerShell. Neither command pins the installer to a reviewed version nor verifies a checksum or cryptographic signature before execution.

The effective code executed by these commands can change after the Skill has been audited. Compromise of the distribution server, hosting account, release process, DNS resolution, or another component of the delivery chain could consequently turn the installation instructions into an arbitrary-code-execution channel. The PowerShell use of Invoke-Expression (iex) presents the same underlying risk as piping curl output into Bash.

Installation is presented as a fallback when oo is unavailable, rather than part of ordinary Benzinga read operations. Nevertheless, automatically executing an unverified installer exceeds the minimum privileges required to query Benzinga. A safer installation workflow would keep software installation outside autonomous Skill execution.

The audit found no evidence in the reviewed file of embedded malicious scripts, persistent services, credential-file access, obfuscation, destructive Benzinga actions, or Agent memory modification. Network transmission of connector action payloads is disclosed and necessary for the declared remote connector functionality.

Attack Path

  1. The oo command is absent, causing the first-time setup fallback to apply.
  2. An Agent or user runs the documented Bash or PowerShell installation command.
  3. The shell retrieves the current installer ...[truncated 1057 chars]
Remediation
View remediation

Remediation Suggestions

  1. Remove direct pipe-to-shell execution and PowerShell Invoke-Expression from the Skill instructions.
  2. Prefer an established package manager or a version-pinned release artifact from a documented release repository.
  3. Download the installer to a local file without executing it automatically.
  4. Publish and verify a cryptographic checksum and, preferably, a signature backed by a documented trusted signing key.
  5. Display the artifact's source, exact version, expected digest, and intended effects before installation.
  6. Require explicit user approval before executing any installer.
  7. Keep installation outside autonomous Skill operation; the Skill should report that the prerequisite is missing and provide safe manual setup guidance.
  8. Run installation with the least-privileged account possible and avoid elevated shells unless a separately reviewed step strictly requires elevation.

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 includes a curl ... | bash installer pattern, which executes a remote script directly from the network without verification. If the remote host, transport, or served script is compromised, the user may run attacker-controlled code on their machine; the fact that this appears in a setup section for a broadly-invoked skill makes it more dangerous because the agent may surface or recommend it during error handling.

Content

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

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description says to use this skill for "ANY Benzinga request" and "instead of calling the API directly," which is an overly broad activation trigger. Broad triggers can cause the agent to invoke this skill in situations where a narrower, safer, or more appropriate tool should be used, increasing the chance of unintended command execution or unsafe setup behavior being surfaced to the user.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.