Back to skill

Security audit

BoxHero

Security checks for vulnerabilities and agentic risk

Overview

The BoxHero features match the description, but setup can execute unchecked software without clear user approval.

Review the setup before installing. Have the CLI installed through a separately reviewed process, require approval before running downloaded installers, and review or disable automatic installation of additional agent skills using the [upstream controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). BoxHero access through OOMOL is disclosed, but the remote installer contents and exact local changes remain unverified.

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
  • 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The supplied chunk performs remote installer execution rather than searching or reading BoxHero data. No shown code establishes that this installation is a supporting dependency for the declared functionality. The downloaded script's contents are unavailable, so its downstream behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a remotely fetched script directly into Bash executes its contents with the agent process's local permissions, without inspection or independent integrity verification. If the distribution endpoint or delivery infrastructure is compromised, the script could access local secrets or modify files; the analogous PowerShell command has the same risk.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

The setup workflow executes remote installation scripts without warning about the local-system impact.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback directs the agent to install software by executing remote scripts without explaining local-system changes or requiring explicit approval. Although limited to a missing-CLI error, this can unexpectedly expand a read-only BoxHero request into local code execution and installation.

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 79)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