Electrical Backup Power

• Outcome: Pass
• Latest audit: Sep 15, 2026 · 1:33 AM UTC
• Version: 1.0.0

Overview

This is a safety-oriented educational skill about backup power, with one install-supply-chain caution but no evidence of hidden, destructive, or deceptive behavior.

Before installing, consider using a pinned or otherwise trusted `clawhub` installer version and install from a low-privilege environment. Treat the electrical guidance as educational safety support, not a substitute for a licensed electrician or local electrical code requirements.

A.I.G

Vulnerability Patterns

• Insecure Dependencies: Introduces malicious components through unsafe dependency sources
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T08 · Insecure Dependencies

Warning

• Location: SKILL.md:15

Finding

Unpinned Package Execution Through npx

Content

View full analysis

Vulnerability Details

File Location: SKILL.md, line 15
Vulnerability Type: Unpinned third-party package execution
Risk Level: Medium

Vulnerable Code

yaml

install: "npx clawhub install howtousehumans/electrical-backup-power"

Technical Analysis

The installation command invokes clawhub through npx without specifying a reviewed package version or integrity hash. If the package is absent locally, npx may retrieve and execute its current release from the configured npm registry.

Consequently, the code executed during installation is not immutable and may differ from the version evaluated when this skill was reviewed. This creates a supply-chain trust boundary involving the package publisher, registry, account security, dependency graph, and local npm configuration.

Attack Path

1. An attacker compromises the package publisher, registry entry, or an upstream dependency used by the unpinned clawhub release.
2. The attacker publishes a malicious or compromised version under the package name resolved by npx.
3. A user runs the documented installation command.
4. npx resolves and downloads the current package release if a suitable trusted local copy is unavailable.
5. Package lifecycle behavior or CLI code executes the attacker's payload under the installing user's account.

Impact Assessment

Successful exploitation could provide arbitrary code execution with the privileges of the user running the installation command. Depending on that user's permissions and environment, the payload could read or modify accessible files, steal environment variables or credentials, alter development configuration, install additional components, or make network requests.

The reviewed project itself contains no malicious scripts, credential access, persistence mechanism, obfuscation, or data-exfiltration implementation. The risk arises specifically from mutable, unverified third-party code execu ...[truncated 25 chars]

Remediation

View remediation

Remediation Suggestions

• Pin clawhub to an explicitly reviewed version instead of allowing npx to resolve a mutable current release.
• Verify the package publisher, provenance, registry source, and published integrity metadata before documenting the command.
• Use a lockfile or equivalent immutable dependency mechanism where the installation workflow supports one.
• Prefer an invocation such as npx --yes clawhub@<reviewed-version> ..., accompanied by documented integrity verification.
• Periodically review and deliberately update the pinned version rather than accepting upgrades implicitly.
• Run installation under a least-privileged account and avoid exposing unnecessary secrets in the installation environment.

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Harmful Content Injection

Critical

• Category: Prompt Injection
• Confidence: 95% confidence

Finding

This content may contain harmful instructions that could cause physical harm if followed. CRITICAL: Review carefully before use.

Content

Scanner excerpt · SKILL.md (reported line 20)May include surrounding context.

install: "npx clawhub install howtousehumans/electrical-backup-power"

Electrical Basics & Backup Power

This is not a home wiring skill -- the survival-basics skill covers outlets and switches. This is about understanding the electrical system in your building and what to do when the grid goes down. Two things kill people in power outages: carbon monoxide from generators run indoors, and electrocution of utility workers from generators backfed into the grid. Both are preventable with basic knowledge. Beyond emergency generators, a basic understanding of solar and battery backup means you can keep critical systems running during extended outages without risking anyone's life, including the lineman working to restore your power.

agent-adaptation

# Localization note -- electrical safety principles are universal. Standards and voltages differ.
# Agent must follow these rules when working with non-US users:
- Safety principles (CO poisoning prevention, backfeed danger) are universal.

Rp1

Medium

• Category: MCP Rug Pull
• Confidence: 97% confidence

Finding

The install command invokes npx clawhub without a pinned package version, which makes installation depend on whatever version is current at execution time. That creates a supply-chain risk: a compromised or breaking upstream release could be fetched and executed unexpectedly.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.