ClawHub
Back to skill

Security audit

Tapfiliate

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Tapfiliate connector, but its setup instructions include unverified remote installer commands that execute downloaded code directly in a shell.

Before installing, review the oo CLI installation path carefully. Prefer an official package manager or manually downloaded, version-pinned installer with checksum or signature verification; do not let an agent run the remote installer automatically. For normal use, confirm any Tapfiliate write action payload before it is run.

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:65
Finding
Unverified Remote Installation Scripts Executed Directly by Shells## Vulnerability Details **File Location**: `SKILL.md`, lines 65–69 **Vulnerability Type**: Remote payload retrieval and execution **Risk Level**: High The first-time setup instructions execute remotely retrieved installation scripts directly in Bash or PowerShell: ```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 Both installation commands combine retrieval and execution into a single operation. The downloaded content is mutable and is not subject to version pinning, cryptographic signature validation, checksum verification, or manual review before execution. Although the URLs use HTTPS and belong to a domain associated with the declared provider, HTTPS does not establish that the returned script is safe or immutable. Compromise of the hosting service, publication pipeline, account, or another trusted delivery component could change the effective payload after the Skill has been reviewed. Redirect behavior or infrastructure compromise could create the same outcome. The installation behavior is only conditionally necessary when the required CLI is absent. Direct remote execution exceeds the minimum privilege and assurance needed to install that dependency because safer, verifiable distribution methods can provide the same functionality. The Skill also instructs the CLI to transmit Tapfiliate action payloads through OOMOL. That network communication is disclosed and functionally necessary for the connector. The reviewed file does not demonstrate credential harvesting or transmission to an unrelated endpoint; therefore, that data flow is not reported as a separate vulnerability. ### Attack Path 1. The `oo` CLI is unavailable, causing the documented first-time setup path to be used. 2. An agent or user copies or executes the recommended Bash or PowerShell command. 3. The c ...[truncated 1288 chars]
Remediation
## Remediation Suggestions 1. Remove all pipe-to-shell and download-to-`iex` installation instructions. 2. Direct users to a version-pinned release artifact or a trusted platform package manager instead of a mutable installation endpoint. 3. Publish a SHA-256 or stronger digest through a separate trusted channel and require verification before execution. 4. Prefer cryptographically signed packages or scripts and document signature verification against a pinned publisher key. 5. Use a staged installation process: download the artifact to a local file, verify its origin and integrity, allow inspection, and only then execute it. 6. Require explicit user approval before dependency installation. The agent should not install software automatically following an authentication or command failure. 7. Execute installation with ordinary user privileges wherever possible and clearly identify any step that genuinely requires elevated permissions. 8. Pin the installer and CLI version so the reviewed instructions cannot silently retrieve different code in the future.

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

External Script Fetching

High
Category
Supply Chain
Content
- **`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
Confidence
95% confidence
Finding
The skill instructs users to install software by piping a remotely fetched script directly into a shell (`curl ... | bash`). This is dangerous because any compromise of the hosting domain, TLS interception in a weakened environment, or accidental script change would result in immediate arbitrary code execution on the user's machine with the user's privileges. In a skill context, this is more dangerous because it is presented as a routine remediation step for command failure, increasing the chance an agent or user executes it without independent verification.

Static analysis

No suspicious patterns detected.