Back to skill

Security audit

Respond.io

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for Respond.io, but its setup instructions include unsafe remote installer commands that could run changing code on the user's machine.

Review the setup path before installing. Prefer installing the oo CLI through a verified package or separately downloaded, inspected, and verified installer. For Respond.io operations, confirm any write or delete payload carefully because the skill can modify CRM/contact data.

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:67
Finding
Unverified Remote Installer Download and Immediate Execution## Vulnerability Details **File Location**: `SKILL.md`, lines 67–71 **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 download mutable scripts from `cli.oomol.com` and pass their contents directly to Bash or PowerShell. Neither installation path pins a release, verifies a cryptographic signature or checksum, nor gives the user an opportunity to inspect the downloaded script before execution. Although HTTPS provides transport protection and server authentication, it does not make the downloaded program immutable or safe. A compromise of the hosting server, publishing account, DNS/control plane, TLS termination infrastructure, or installer build pipeline could cause users to execute attacker-controlled code. The effective payload can also change after this Skill has been reviewed. Installing the required CLI may be necessary for the declared Respond.io integration, but executing an unverified remote response directly in an interpreter exceeds the minimum mechanism necessary to perform that installation. ### Attack Path 1. A user attempts to use the Skill on a system where the `oo` CLI is unavailable. 2. The action fails with `oo: command not found`. 3. The user or agent follows the documented first-time setup command. 4. An attacker who has compromised the installer host or its delivery infrastructure replaces the expected installer with a malicious script. 5. `curl | bash` or `irm | iex` passes the response directly to the local interpreter. 6. The malicious payload executes with the privileges of the invoking user before any integrity or content validation occurs. 7. The payload can access data available to that user, alter the environment, or install additional component ...[truncated 816 chars]
Remediation
## Remediation Suggestions 1. Remove all direct `curl | bash` and `irm | iex` installation patterns. 2. Prefer a trusted platform package manager or a pinned release artifact from the verified upstream repository. 3. Pin the installer or binary to an explicit version rather than retrieving a mutable default script. 4. Download the artifact to a local file without executing it: ```bash curl --proto '=https' --tlsv1.2 -fL \ -o oo-installer.sh \ 'https://verified.example/path/to/versioned/install.sh' ``` 5. Publish and verify a SHA-256 digest through an independently protected channel: ```bash echo '<EXPECTED_SHA256> oo-installer.sh' | sha256sum --check - ``` 6. Prefer cryptographic release-signature verification over checksums alone, and document the trusted signing key and fingerprint. 7. Allow users to inspect the downloaded file before explicitly executing it. 8. Avoid requiring administrator privileges unless the selected installation destination strictly requires them. 9. On Windows, download the script separately, validate its Authenticode signature or a separately published cryptographic digest, and only then invoke it. 10. Document the expected files, network destinations, and permission changes made by installation so users can assess whether the installer observes least privilege.
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
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
98% confidence
Finding
The skill instructs the agent to install software by piping a remotely fetched script directly into a shell (`curl ... | bash`). This creates a supply-chain and remote code execution risk: if the install endpoint, transport, or upstream distribution is compromised, arbitrary code will run immediately on the host with the user's privileges.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The description says to use this skill for "ANY Respond.io request" and "Whenever a task involves Respond.io," which is an extremely broad activation condition. It does not define narrower trigger phrases, constraints, or exclusion cases, so ordinary references to Respond.io could invoke the skill unintentionally.

Static analysis

No suspicious patterns detected.