Back to skill

Security audit

SmartHR

Security checks for vulnerabilities and agentic risk

Overview

SmartHR operations have clear approval controls, but automatic installation executes unverified remote code and may introduce broader agent changes.

Review and approve CLI setup separately before using this skill. Verify the installer and release, and check or disable automatic installation of other agent skills. Installer contents could not be retrieved during this review. Connect only the necessary SmartHR permissions, understand OOMOL's role in handling HR data, and retain the required approval for every write or deletion.

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
96% confidence
Finding

The supplied chunk runs an external installer rather than performing SmartHR operations. Although dependency installation can be a supporting implementation detail, nothing provided establishes this installer's relationship to SmartHR. The downloaded script's contents and subsequent effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a remotely downloaded script directly into bash executes mutable external code without checking a pinned version, integrity, or authenticity beyond HTTPS. Compromise of the distribution endpoint could therefore execute arbitrary commands with the agent's local privileges, potentially exposing accessible credentials and files; the PowerShell example has the same risk. The legitimate CLI dependency and conditional setup reduce exposure but do not remove this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 108)May include surrounding context.

First-time setup executes downloaded scripts without warning about remote-code execution or system changes.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The setup instructions direct the agent to execute a remote installer without explaining its local execution privileges or requiring explicit approval for system changes. Restricting setup to a missing-CLI error reduces exposure, but the SmartHR write-confirmation rules do not clearly cover installing software on the user's machine.

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 129)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