Back to skill

Security audit

Roomba Control

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple local reference-documentation tool and I found no evidence that it reads credentials, uses the network, persists, or changes the system.

This appears safe to install as a lightweight reference skill, but users should treat the Roomba Control content as generic guidance rather than authoritative product documentation.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/script.sh (reported line 64)May include surrounding context.

sh
## Prerequisites
- Basic understanding of devtools concepts
- Required tools and access credentials
- System meeting minimum requirements

## Installation

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description repeatedly presents the skill as a general-purpose 'Reference tool for life' and 'Quick lookup' resource, which is broad enough to overlap with common requests rather than narrowly scoping when this skill should activate. The file lists command names, but it does not provide explicit trigger conditions, exclusions, or negative examples to prevent unintended invocation outside the Roomba Control domain.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
74% confidence
Finding

The file comment frames the script as a Roomba Control reference tool for devtools contexts. However, much of the embedded documentation is generic boilerplate about networking, migrations, monitoring, and system tooling, which does not specifically reflect that stated intent and weakens the claimed specialization.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The manifest says this is a 'Reference tool' and 'Quick lookup' for Roomba Control concepts and patterns, which suggests concise reference material. The implemented commands expand into tutorial, migration, debugging, performance, and security guide content, making the behavior materially broader than the narrowly described quick-lookup scope.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.