Back to skill

Security audit

Payhip

Security checks for vulnerabilities and agentic risk

Overview

Payhip changes require your approval, but the required CLI can also change installed agent skills without this skill explaining that behavior.

Review the CLI's automatic skill installation before proceeding. Consider setting OO_SKILLS_SYNC_DISABLED=1 for CLI calls and reviewing the installer separately. OOMOL will mediate connected Payhip access. Keep the required approvals for coupon and license changes. The delivered installer and hosted connector were not inspected, so their exact behavior remains uncertain.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The visible code performs remote software installation rather than Payhip data operations. Although installation can be a supporting implementation detail, this chunk provides no evidence connecting the Oomol installer to the declared functionality. The downloaded script is not supplied, 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

The setup instructions pipe a remotely fetched script directly into Bash, and the Windows alternative similarly executes fetched content without verification. A compromised distribution endpoint or malicious installer update could execute arbitrary code with the agent process's permissions, exposing accessible files and credentials; conditional installation reduces exposure but does not establish installer integrity.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

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 84)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