Back to skill

Security audit

TalentHR

Security checks for vulnerabilities and agentic risk

Overview

Employee-role changes require confirmation, but the setup instructions can execute downloaded software without separately asking the user.

Review and install the CLI separately before enabling this skill, rather than allowing the automatic download-and-execute fallback. Check whether its bundled-skill synchronization should be disabled; the publisher documents OO_SKILLS_SYNC_DISABLED in its [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). Understand that OOMOL mediates access to your connected TalentHR account, and confirm the employee and intended role before every change. The installer and hosted connector were not verified.

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 visible code installs software from an Oomol-hosted endpoint rather than interacting with TalentHR. Nothing in the supplied chunk establishes this installation as a supporting dependency for the declared purpose. The remote script's contents are unavailable, so its additional behavior cannot be assessed.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a live HTTPS response directly into bash executes remote code with the invoking user's permissions without a pinned version or independent integrity verification. A compromised distribution endpoint or release pipeline could compromise the local environment; the PowerShell alternative has the same weakness, although installation is only requested when the CLI is missing.

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

Fallback setup executes downloaded installation scripts without warning about local system changes or requesting approval.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The fallback directs an agent to install software when the CLI is missing without explicitly requiring approval for local system changes. Confirmation rules cover TalentHR writes and destructive actions, not local installation, leaving a consent gap even though the missing-command condition limits exposure.

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 76)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