Back to skill

Security audit

Energy Performance Certificates

Security checks for vulnerabilities and agentic risk

Overview

The certificate searches fit the stated purpose, but automatic setup executes unverified downloaded code without a clear approval step.

Review setup before installing. Prefer an independently verified, version-pinned CLI installation and explicitly approve its system changes. Expect certificate requests to pass through OOMOL. The publisher's [command reference](https://raw.githubusercontent.com/oomol-lab/oo-cli/main/docs/commands.md) documents OO_SKILLS_SYNC_DISABLED to prevent automatic agent-skill synchronization. The remote installer contents and exact installed-release behavior remain unverified.

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 does not access the declared Energy Performance Certificate service or perform any certificate-data operation. It instead executes an installer from an unrelated service, with no demonstrated connection to the declared purpose. The remote script's contents are not supplied, so its further behavior cannot be assessed.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The only supplied command initiates login and contains no EPC query, retrieval operation, or reference to the declared service. Authentication could support a larger implementation, but the supplied chunk provides no evidence connecting this login to EPC access.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a mutable remote script directly into Bash without verifying its contents, integrity, or release version; the PowerShell alternative has the same problem. Compromise of the installer distribution path could yield arbitrary code execution with the agent's privileges. HTTPS and the domain's relevance to the documented CLI reduce some concerns but do not protect against a compromised publisher or distribution service.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

Fallback setup executes downloaded installation scripts without warning the user about the system changes or obtaining approval.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

A missing CLI triggers instructions to execute an installer without first obtaining approval for software installation or explaining its system changes. A request to read certificate data does not itself authorize arbitrary installer execution, which can modify files and configuration with the agent's privileges. The conditional fallback reduces exposure but does not establish user consent.

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 79)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