Back to skill

Security audit

RepairShopr

Security checks for vulnerabilities and agentic risk

Overview

The RepairShopr features fit the stated purpose, but setup tells the agent to execute unverified downloaded installers without first obtaining your approval.

Review and approve the CLI installation separately before allowing setup to run, including any automatic agent-skill synchronization. Connect only an authorized RepairShopr account and consider that OOMOL mediates access to customer and ticket data. The remote installer was not available for content inspection, so its exact changes are 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 installs or bootstraps software from an unrelated service; it contains no visible RepairShopr functionality. Nothing in the supplied chunk establishes this installation as a supporting dependency for RepairShopr access. The downloaded 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
86% confidence
Finding

Authentication could support a RepairShopr integration, but the supplied chunk contains only a login command and establishes no connection to RepairShopr. As supplied, its primary behavior does not substantiate the declared search-and-read purpose. No credential theft or additional resource access can be inferred from this command alone.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command streams a mutable remote script directly into Bash without verifying an independently trusted signature or digest; the PowerShell alternative has the same execution pattern. Compromise of the distribution endpoint could execute attacker-controlled code with the agent's local privileges, exposing accessible files and credentials; HTTPS and the conditional setup trigger reduce some exposure but do not verify the delivered code.

Content

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

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

Medium
Category
Output Handling
Confidence
95% confidence
Finding

A missing CLI triggers instructions to install software by executing remote scripts, without requiring disclosure of system changes or explicit user approval. Although conditional and plausibly legitimate setup, this expands a read-only RepairShopr request into local code execution; the declared tool restriction may limit execution but does not make the fallback instruction 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 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