Back to skill

Security audit

Rakuraku Seisan

Security checks for vulnerabilities and agentic risk

Overview

The business-data workflow has clear approval rules, but setup can execute unverified remote code and introduce persistent agent skills without clearly scoped user approval.

Review setup before installing. Install a reviewed CLI version separately and disable unwanted agent-skill synchronization. Confirm that OOMOL may process your business data, approve each import's contents, and avoid publicly exposing confidential CSVs. The remote installers remain unverified; the artifacts do not establish malicious intent.

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
93% confidence
Finding

The visible code installs external software rather than accessing Rakuraku Seisan data. Although dependency installation can be a supporting implementation detail, this chunk provides no evidence that the Oomol installer supports the declared purpose. The downloaded script's contents and further effects cannot be determined from the supplied code.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The curl-to-bash pipeline executes the current contents of a remote installer without pinning or verifying the artifact. HTTPS protects transport but does not prevent a compromised publisher or hosting service from supplying malicious code, which could access local files and credentials. The endpoint is relevant to the documented CLI dependency, reducing suspicion of malicious intent but not the supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

The setup workflow executes remotely downloaded installation scripts without warning about the system-integrity risk.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The setup instructions pipe remotely fetched shell and PowerShell scripts directly into interpreters without integrity verification or an explicit installation approval step. A compromised distribution endpoint could execute arbitrary code with the invoking user's privileges; limiting installation to a missing-CLI error reduces frequency but not impact. This overlaps with SC2 rather than representing an independent exploit path.

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 78)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