Back to skill

Security audit

OSV

Security checks for vulnerabilities and agentic risk

Overview

The vulnerability lookup workflow is coherent, but missing software can trigger execution of downloaded installers without clear user approval.

Review the setup before enabling this skill. Install a reviewed, pinned CLI release yourself and require approval before downloaded code runs. Consider whether routing package queries through OOMOL and its billing model suits your needs. The external installers and CLI implementation were not audited; the Review verdict concerns setup control, with no artifact evidence establishing 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 (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command installs or bootstraps external software through remote shell execution; it does not search or read OSV data. Nothing in the supplied chunk establishes that this installer is a supporting dependency for OSV access. The remote script's contents and further effects are not available for assessment.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The supplied chunk performs only a login operation, rather than the declared OSV searching and reading. Authentication could be a supporting implementation detail if its relationship to OSV were established, but no such relationship or subsequent OSV functionality is present in the supplied code.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

The command pipes a mutable remote script directly into Bash without a pinned version or independent integrity verification. HTTPS protects transport but does not prevent a compromised distribution endpoint or malicious installer update from executing code with the agent process's permissions; the missing-CLI condition limits exposure but does not mitigate execution once triggered.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

The fallback setup instructs the agent to execute downloaded installer scripts without warning the user about remote code execution or system changes.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

A missing CLI triggers instructions to execute a downloaded shell or PowerShell installer without first obtaining approval for code execution and system changes. Although dependency setup is relevant to the workflow, a request to read OSV data does not itself authorize arbitrary installation, and a compromised installer could act with the agent process's 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 71)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