Back to skill

Security audit

Cert Spotter

Security checks for vulnerabilities and agentic risk

Overview

The Cert Spotter workflow is coherent, but its setup can automatically execute unverified downloaded software without asking you first.

Review the setup before installing. Install the required CLI yourself from a verified release, and require approval before any downloaded installer runs. OOMOL will mediate account access; the external installer and connector implementations were not verified. Account changes and deletions already require your confirmation.

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 supplied code performs no visible Cert Spotter operations. Instead, it executes an installer hosted by a different service, with no demonstrated connection to the declared purpose. This is a material resource and capability mismatch, rather than an established supporting implementation detail. The downloaded script's contents and effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The curl-to-bash command immediately executes mutable remote content without verifying a pinned artifact or trusted signature. HTTPS protects transport but does not protect against a compromised installer host or malicious upstream changes, which could result in arbitrary code execution under the user's account; the PowerShell alternative has the same weakness.

Content

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

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

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback setup directs the agent to execute downloaded shell or PowerShell code without an explicit installation approval step or an integrity-verification requirement. Although limited to a missing-CLI error and plausibly legitimate, this can turn a Cert Spotter task into local code execution with the invoking user's privileges if the installer source is compromised.

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