Back to skill

Security audit

Booqable

Security checks for vulnerabilities and agentic risk

Overview

The Booqable reads fit the stated purpose, but setup can execute downloaded code without a separate approval or integrity check.

Review and approve CLI setup separately before allowing Booqable requests. Prefer a pinned, independently verified installation and check which agent skills it installs or updates. Connect only the account and permissions needed, and understand that OOMOL mediates access to business data. The full bundled artifact was inspected, but the remote installers and hosted service implementation remain unverified; no malicious behavior was established.

Vulnerability Patterns
  • 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
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command performs remote-script execution, not the declared Booqable data access. Although installing a CLI could be a supporting implementation detail, the supplied chunk establishes no relationship between this installer and Booqable. The downloaded script is not provided, so its further effects cannot be determined.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 40)May include surrounding context.

md
## Available actions

- `get_current_company` — Fetch the current Booqable company connected to the access token.
- `get_customer` — Fetch one Booqable customer by id.
- `get_order` — Fetch one Booqable order by id.
- `get_product_group` — Fetch one Booqable product group by id.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a mutable network response directly into Bash without a pinned version or independent integrity verification; the PowerShell alternative uses the same download-and-execute pattern. Compromise of the installer distribution path could execute arbitrary code with the agent process's privileges, although the missing-CLI condition limits when this exposure occurs and no malicious installer content is shown.

Content

Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.

The setup workflow instructs the agent to execute downloaded installer scripts without warning the user about remote code execution or system changes.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback instructs the agent to install software after a missing-command error without requiring informed approval for executing remote code or changing the local environment. Although conditional and relevant to setup, this expands a read-only Booqable request into a materially different operation that the user may not have authorized.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 85)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources