ClawHub
Back to skill

Security audit

Recall.ai

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its Recall.ai purpose, but its setup instructions include unverified remote installer commands that could run arbitrary code on a user's machine.

Review the installer path before installing. Prefer installing the oo CLI from a signed, versioned, or package-managed source, and do not run the curl-to-bash or PowerShell iex commands unless you trust OOMOL's installer delivery. For Recall.ai changes, verify the exact bot, media, or meeting target before approving write or destructive actions.

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:59
Finding

Unverified Remote Installer Download and Immediate Execution

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 59–63
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 an external server and immediately execute them using Bash or PowerShell. Neither command pins the installer to a reviewed version nor verifies a cryptographic signature or checksum before execution.

HTTPS protects the connection in transit but does not establish that the current remote script is identical to the version intended or reviewed when this Skill was published. The effective code can change without any modification to the audited project. Compromise of the hosting service, domain, TLS infrastructure, release pipeline, or OOMOL account controlling the installer could therefore turn these commands into an arbitrary-code execution channel.

Although installing the required CLI is related to the Skill's functionality and the instructions only recommend installation after an oo: command not found error, executing an unverified remote script exceeds the minimum privilege needed to provide installation guidance. The project contains no local copy of the installer from which its behavior or required permissions can be audited.

Attack Path

  1. The oo CLI is unavailable, or the user receives an oo: command not found error.
  2. The user or agent follows the first-time setup instructions in SKILL.md.
  3. The command retrieves the current install.sh or install.ps1 payload from cli.oomol.com.
  4. No checksum, signature, immutable version, or script content is verified.
  5. Bash or PowerShell executes the downloaded response immediately.
  6. If the remote endpoint or its delivery ...[truncated 892 chars]
Remediation
View remediation

Remediation Suggestions

  1. Remove the direct curl | bash and irm | iex installation patterns.
  2. Prefer a trusted operating-system package manager or a signed installer obtained from a versioned, immutable release.
  3. Pin the installer to a specific release rather than a mutable generic URL such as install.sh or install.ps1.
  4. Publish cryptographic checksums and signatures through an independently protected channel, and require verification before execution.
  5. Download the installer to a local file first so users can inspect it before running it. For example, separate retrieval, integrity verification, and execution into distinct commands.
  6. Document the files, network endpoints, environment changes, and permissions required by the installer.
  7. Avoid requiring administrator privileges unless a specific installation step needs them; clearly identify and isolate any privileged operation.
  8. If automated installation is essential, include a reviewed installer in the release artifact or use a reproducible, signed distribution mechanism whose integrity can be independently verified.

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 running a remote installation script via 'curl ... | bash', which executes unpinned code fetched at runtime with no integrity verification. If the remote host, distribution path, or network path is compromised, this becomes arbitrary code execution on the user's machine.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger language is overly broad and instructs the agent to use this skill for any Recall.ai-related request, which can cause the skill to be invoked on ambiguous or incidental mentions. In an agent setting, that broad routing increases the chance of unintended tool use and can bypass more precise user-intent checks before performing connector-backed actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.