ClawHub
Back to skill

Security audit

Reducing Entropy

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed code-simplification checklist skill, with install-chain and over-deletion cautions but no evidence of hidden execution, credential access, exfiltration, or deception.

Install only from a source you trust, preferably with a pinned version or reviewed commit. When using the skill, treat deletion advice as a prompt for review rather than an automatic instruction: preserve security checks, required logs, compliance code, and tests for behavior that still exists, and run the relevant test suite before accepting changes.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
README.md:27
Finding

Unpinned Third-Party Installer Creates a Supply-Chain Execution Risk

Content
View full analysis

Vulnerability Details

File Location: README.md, lines 27–29
Vulnerability Type: T08: Insecure Dependencies
Risk Level: Medium

Vulnerable code snippet:

bash
npx add https://github.com/wpank/ai/tree/main/skills/testing/reducing-entropy

Technical Analysis

The documented installation procedure invokes the npm package named add through npx without pinning its package version or integrity hash. If that package is absent locally, npx may retrieve and execute it from the configured npm registry.

The installer also receives a URL referencing mutable content in a personal GitHub repository. The URL does not pin the source to a reviewed commit, immutable release artifact, checksum, or cryptographic signature. Therefore, both the installer behavior and installed content may differ from what was reviewed during this audit.

This is a supply-chain weakness rather than evidence that the currently documented package or repository is malicious.

Attack Path

  1. An attacker compromises the npm package, its publisher account, the configured package registry, the GitHub account, or the upstream repository.
  2. The attacker publishes a malicious installer version or modifies the content referenced by the mutable repository URL.
  3. A user copies and runs the documented npx add ... command.
  4. npx retrieves and executes the unpinned installer under the user's account.
  5. The compromised installer accesses or modifies resources available to that user, or installs altered Skill instructions that affect subsequent Agent behavior.

Impact Assessment

Successful exploitation could execute arbitrary code with the permissions of the user running the installation command. Depending on that user's environment, the resulting scope may include:

  • Reading or modifying files accessible to the user.
  • Altering project or user-level Agent configuration.
  • Installing malicious or modified Skill instru ...[truncated 388 chars]
Remediation
View remediation

Remediation Suggestions

  1. Replace the unversioned npx add invocation with a trusted installer pinned to an exact package version.
  2. Pin the Skill source to a reviewed Git commit or immutable release tag rather than a mutable branch.
  3. Publish and verify a cryptographic checksum or signature for the downloaded artifact.
  4. Use npx --no-install when relying on an installer that must already be installed and independently verified.
  5. Prefer a transparent installation process that downloads a fixed archive, verifies its digest, and copies only the expected files.
  6. Document the exact expected files and hashes so users can validate the installed content.
  7. Run installation with least privilege and avoid exposing unrelated credentials or sensitive environment variables to the installer.

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 36)May include surrounding context.

From your project root:

bash
mkdir -p .cursor/skills
cp -r ~/.ai-skills/skills/testing/reducing-entropy .cursor/skills/reducing-entropy

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 52)May include surrounding context.

From your project root:

bash
mkdir -p .claude/skills
cp -r ~/.ai-skills/skills/testing/reducing-entropy .claude/skills/reducing-entropy

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

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

Claude Code (global)

bash
mkdir -p ~/.claude/skills
cp -r ~/.ai-skills/skills/testing/reducing-entropy ~/.claude/skills/reducing-entropy

External Model or Provider Selection

Medium
Category
Excessive Agency
Confidence
90% confidence
Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: reducing-entropy
model: reasoning
category: testing
description: Minimize total codebase size through ruthless simplification. Measure success by final code amount, not effort. Bias toward deletion.
version: 1.0

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill repeatedly instructs users to delete code, tests, and abstractions with a strong bias toward reduction, but it does not pair that advice with safeguards such as validating business requirements, preserving security checks, confirming backups, or requiring regression testing. In practice, this can drive unsafe removals of protections, monitoring, or test coverage under the banner of simplification, increasing the chance of security regressions or destructive changes.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.