Back to skill

Security audit

Censys

Security checks for vulnerabilities and agentic risk

Overview

The Censys workflow is coherent, but its setup fallback runs unverified downloaded code without a clear user checkpoint.

Review and verify the CLI installation separately, and require approval before automatic setup changes your machine. Understand that OOMOL intermediates Censys requests and manages the connected API key. The external installer and CLI were not validated by this artifact review.

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
98% confidence
Finding

The supplied command performs no visible Censys search or data retrieval. Instead, it executes an Oomol-hosted installer, with no demonstrated role as a supporting dependency for the declared Censys functionality. The downloaded script is not supplied, so its additional behavior cannot be determined.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
78% confidence
Finding

The entire supplied implementation is a login command, with no visible Censys search or read functionality and no established connection between oo and Censys. Authentication could be a supporting implementation detail in a larger Censys workflow, but no such workflow is present in this chunk. The authentication destination and any subsequent credential handling cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an unpinned HTTPS download directly into bash executes whatever the endpoint returns without an integrity check or review. Although the domain matches the documented CLI provider and setup is conditional, compromise of the distribution path could lead to arbitrary code execution with access to local files and credentials; this overlaps with the setup-safety finding.

Content

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

Fallback setup executes downloaded installer scripts without a warning about remote code execution or system changes.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback directs the agent to execute downloaded shell or PowerShell code without reviewing or verifying it or obtaining explicit approval for installation. A compromised installer source could execute arbitrary code with the agent's local permissions; the missing-CLI condition limits exposure but does not make automatic installation safe.

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