Back to skill

Security audit

DataForB2B

Security checks for vulnerabilities and agentic risk

Overview

The data-search workflow fits its purpose, but fallback setup directs the agent to execute unverified remote installers without clear user control over local changes.

Review setup before enabling this skill. Prefer a separately approved, version-pinned CLI installation with verified integrity, and check which agent skills it installs or updates. DataForB2B requests use your OOMOL-connected account and may consume service credits. The Review verdict concerns installation control and broader local changes, not evidence of 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
99% confidence
Finding

The declared purpose concerns DataForB2B data access, while the code executes an installer hosted on cli.oomol.com. Nothing supplied establishes this installer as a supporting dependency for DataForB2B. The remote script's contents and downstream effects are unknown, but downloading and executing it is directly observable and is not represented by the description.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an HTTPS response directly into Bash executes mutable remote content without an independently verified digest, signature, or pinned version. Compromise of the installer hosting or release process could execute arbitrary code with the agent's permissions, potentially exposing accessible files and credentials; the PowerShell fallback has the same trust problem.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

The setup workflow executes remotely downloaded installation scripts without warning about local code execution and system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The missing-CLI fallback directs the agent to execute remote installation scripts without explicitly obtaining approval for local code execution and system changes. Conditional execution limits exposure, but a request to read business data does not necessarily authorize installing software with the agent's local permissions.

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 82)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