Back to skill

Security audit

CUFinder

Security checks for vulnerabilities and agentic risk

Overview

The CUFinder lookups fit the stated purpose, but the required CLI can silently install other agent skills without this skill disclosing that effect.

Review the CLI's broader installation effects before allowing setup. If you only want CUFinder access, configure OO_SKILLS_SYNC_DISABLED=1 before invoking oo; this documented control disables startup skill synchronization. Independently review the installer and installed version. Submit only lookup data you are authorized to share with OOMOL and CUFinder, and check applicable usage charges. The remote installer and complete CLI runtime were not audited.

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
99% confidence
Finding

The supplied code contains no CUFinder search or read operation. Instead, it executes a remote installer from cli.oomol.com, with no demonstrated connection to the declared CUFinder functionality. This is an undeclared capability and accesses an inconsistent resource. The installer's downstream behavior cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The supplied chunk only initiates a CLI login and contains no CUFinder search or read operations. Authentication could support the declared purpose, but the supplied content does not establish any connection between this login command and CUFinder.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The setup command immediately executes a mutable remote script without pinning a version or verifying an independently trusted signature or digest; the PowerShell alternative has the same weakness. Compromise of the distribution endpoint could execute arbitrary code with the invoking user's privileges, although the missing-CLI prerequisite and the declared Bash(oo *) tool restriction limit exposure if enforced.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

The action workflow lacks a privacy warning before transmitting personal lookup data to third-party services.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The workflow instructs the agent to submit action payloads through OOMOL to CUFinder, including names, employers, or email addresses for the supported enrichment actions. Although the connector is identified, the skill does not warn that personal lookup inputs are disclosed to these services, and line 48 treats all untagged reads as safe to run directly.

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 80)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