Back to skill

Security audit

ShipBob

Security checks for vulnerabilities and agentic risk

Overview

The ShipBob workflow fits its purpose, but setup directs the agent to execute unchecked remote installers without an explicit approval step.

Review before installing. Use a separately reviewed CLI release and explicitly approve local installation changes. Check its automatic skill-installation settings and confirm that OOMOL may access your ShipBob data. The installer and server-side connector implementation are outside the inspected bundle; 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
96% confidence
Finding

The supplied chunk runs an Oomol installation script rather than accessing ShipBob data. Dependency installation could be a supporting implementation detail, but the supplied content establishes no relationship between this installer and the declared ShipBob functionality. The downloaded script's contents and further effects are not shown.

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 41)May include surrounding context.

md
## Available actions

- `get_inventory_level` — Get aggregated ShipBob inventory levels for one inventory item.
- `list_channels` — List ShipBob channels available to the authenticated Personal Access Token.
- `list_inventory_levels` — List ShipBob inventory levels with optional item and product filters.
- `list_locations` — List ShipBob fulfillment network locations.
- `list_products` — List ShipBob products with optional catalog filters.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an unpinned remote script directly into bash executes whatever the endpoint supplies with the invoking user's privileges, without an independent integrity check or review opportunity. HTTPS protects transport but not against a compromised distribution endpoint or malicious release; the PowerShell fallback uses the same download-and-execute pattern. The setup-only condition reduces exposure, and enforced tool restrictions might block execution, but neither makes the prescribed mechanism safe.

Content

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

First-time setup executes downloaded installation scripts without warning about local system changes.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The setup fallback directs the agent to install software after a missing-command error without first explaining local system changes or obtaining approval. A request to read ShipBob data does not itself authorize installing software, although the conditional fallback limits when this exposure occurs.

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 80)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