ClawHub
Back to skill

Security audit

Freshteam

Security checks for vulnerabilities and agentic risk

Overview

The Freshteam skill is mostly purpose-aligned, but its setup instructions include direct execution of remote installer scripts, which needs review before use.

Review the setup steps before installing. Prefer installing the oo CLI through a trusted, versioned, verifiable method, and only connect a Freshteam account with the minimum access needed for the HR or recruiting data you intend to query.

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:63
Finding

Unverified Remote Installer Download and Immediate Execution

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 63–67
Vulnerability Type: 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 mutable scripts from cli.oomol.com and immediately execute them through Bash or PowerShell. Neither command pins an installer version, verifies a cryptographic signature or checksum, nor allows inspection before execution.

The domain is consistent with the declared OOMOL service, but the remote installer is not included in the audited project. Its contents and future changes therefore cannot be verified by this audit. If the hosting service, publishing pipeline, domain, or delivery path is compromised, an attacker can replace the installer with arbitrary code.

This installation mechanism exceeds the minimum privileges required to document use of the Freshteam connector because it creates a general-purpose code-execution path during setup. The PowerShell irm | iex instruction has the same security properties as curl | bash.

Attack Path

  1. A user or agent attempts to use the Skill on a system where the oo CLI is unavailable.
  2. The documented fallback directs the user or agent to execute one of the installer pipelines.
  3. The command downloads the current script from the remote OOMOL endpoint.
  4. Bash or PowerShell interprets the response immediately, without integrity or authenticity verification beyond transport-level TLS.
  5. If the remote script or its delivery infrastructure has been compromised, attacker-controlled commands execute with the privileges of the invoking user.

Impact Assessment

Successful exploitation provides arbitrary code execution under the current user's account. The reachable impact can include:

  • Reading, modifying, or del ...[truncated 597 chars]
Remediation
View remediation

Remediation Suggestions

  1. Remove both direct execution pipelines:
    • Do not pipe curl output into Bash.
    • Do not pipe Invoke-RestMethod output into Invoke-Expression.
  2. Prefer a trusted operating-system package manager or another distribution mechanism that supports signed, versioned releases.
  3. Pin installation instructions to a specific CLI version rather than a mutable install.sh or install.ps1 endpoint.
  4. If standalone installers are necessary:
    • Download the installer to a local file.
    • Download or publish its expected SHA-256 checksum.
    • Verify the checksum before execution.
    • Verify a cryptographic signature tied to a documented publisher key.
    • Stop installation if any verification fails.
    • Execute the verified local file only after allowing inspection.
  5. Avoid elevated execution unless a specific installation step requires it, and document the exact files and permissions affected.
  6. Publish reproducible installer source and release artifacts so reviewers can compare the downloaded payload with the audited version.
  7. Redirect users to a versioned installation guide rather than embedding commands that immediately execute remotely controlled content.

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
98% confidence
Finding

The skill recommends installing software via a shell pipeline that downloads a remote script and executes it immediately (curl ... | bash). If the install endpoint, CDN, TLS termination, or upstream release process is compromised, an agent or user following this guidance could execute arbitrary code on the local system with the user's privileges.

Content

Scanner excerpt · SKILL.md (reported line 63)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 Freshteam request" and "Whenever a task involves Freshteam," which is extremely broad and lacks boundaries or negative examples. This can cause unintended invocation for loosely related mentions of Freshteam rather than clearly scoped actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.