Back to skill

Security audit

Paystack

Security checks for vulnerabilities and agentic risk

Overview

The skill needs review because it allows payment checkout creation without confirming the details and executes an unverified installer during setup.

Require confirmation of checkout details before initialization. Review and verify the CLI installer separately, and review or disable its automatic skill synchronization. OOMOL will mediate access to your connected Paystack data. The remote installer and connector implementation were unavailable for inspection; no malicious behavior was established.

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 (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The visible code performs remote software installation rather than interacting with Paystack. Although installation can be a supporting implementation detail, the supplied chunk establishes no relationship between this installer and the declared purpose. The remote script's contents are unavailable, so its additional behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

Piping a remotely fetched installer directly into bash executes mutable network content with the invoking user's privileges, without a pinned version or independent integrity verification. The legitimate dependency relationship and missing-CLI prerequisite reduce suspicion of malicious intent, but a compromised distribution endpoint could still enable local code execution; the PowerShell alternative has the same weakness.

Content

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

Transaction initialization is classified as a read, bypassing write confirmation.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The initialize_transaction action creates a payment transaction and checkout details but lacks a write tag, causing the safety instructions to classify it as a read that can run without confirmation. This can create unintended payment state using unconfirmed transaction parameters, although initialization alone does not establish that a customer is charged.

Content

No source excerpt is available for this finding.

The safety instructions permit transaction initialization without warning or confirmation by incorrectly treating all untagged actions as reads.

Medium
Category
Output Handling
Confidence
98% confidence
Finding

The blanket rule that untagged actions are reads makes missing annotations fail open, allowing transaction initialization to bypass the intended confirmation boundary. This is the same underlying vulnerability as SDI-4, not an additional independent impact.

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