Back to skill

Security audit

Postmark

Security checks for vulnerabilities and agentic risk

Overview

The Postmark workflow is coherent, but missing-dependency setup executes an unverified remote installer without a clear approval step.

Review and independently verify the CLI installation before allowing automatic setup. Check its bundled-skill synchronization settings and understand that OOMOL handles requested Postmark data. Keep the skill's confirmation requirement for sending emails and changing templates. All bundled artifact content was inspected; external installer behavior remains 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
97% confidence
Finding

The visible behavior is remote software installation, not interaction with Postmark. Nothing in the supplied chunk establishes that this installer is a supporting dependency for Postmark access. The downloaded script's contents are not supplied, so its subsequent actions cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an HTTPS download directly into bash executes whatever script the endpoint supplies, without version pinning, integrity verification, or prior inspection. A compromised distribution endpoint could therefore execute arbitrary commands with the agent's local privileges; the PowerShell alternative has the same risk. The legitimate setup context and missing-CLI condition reduce exposure but do not remove this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

The setup workflow executes downloaded installation scripts without warning the user about local system changes.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The missing-CLI fallback instructs the agent to execute a remote installer without first explaining local system changes or requesting installation approval. Although this is a legitimate dependency setup step triggered only by an error, it extends a Postmark task into local software installation without an explicit consent boundary.

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 87)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