Back to skill

Security audit

HelpDesk

Security checks for vulnerabilities and agentic risk

Overview

The HelpDesk workflow has clear safeguards, but setup downloads and runs software without a separate installation approval step.

Review and approve CLI installation separately, including any bundled-skill changes. Prefer an inspected, version-pinned installation. Connect only the intended HelpDesk account through OOMOL and retain the documented confirmations for edits and deletions. The downloaded installers and hosted implementation 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
98% confidence
Finding

The supplied chunk performs remote script execution for an Oomol installer and contains no HelpDesk operations or evidence connecting that installer to HelpDesk functionality. This is a material capability and resource mismatch, not merely an established supporting implementation detail. The downloaded script's contents and subsequent effects are not available for assessment.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The command pipes a mutable remote script directly into Bash, allowing the fetched content to execute with the invoking user's permissions without prior inspection or independent integrity verification. HTTPS protects transport but does not prevent a compromised publisher or distribution endpoint from serving malicious code; the missing-CLI condition limits frequency, not execution impact.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

The setup workflow executes remote installation scripts without warning about local system changes or third-party code execution.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The missing-CLI fallback instructs the agent to execute third-party installation code without explicitly obtaining approval for local system changes. Restricting setup to an actual command-not-found error reduces exposure, but a request to manage HelpDesk records does not itself authorize installing software.

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 83)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

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 88)May include surrounding context.

md
## Resources

- HelpDesk homepage: https://www.helpdesk.com
- API documentation: https://api.helpdesk.com/docs