Back to skill

Security audit

Principled Simplicity Skill

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign because the reported issues are limited to unpinned installation sources and a low-severity scope concern, with no malicious findings reported; scanner coverage is partial.

Consider that installation may retrieve changed CLI or skill content unless the versions are pinned. The verdict is benign, but not risk-free: Skillspector coverage was partial (93.3%), with SKILL.md partly inspected because its manifest could not be parsed and the binary image outside that analyzer’s scope.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (9)

MCP server referenced without pinned version: 'npx skills'.

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.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The installation command invokes an unpinned npm CLI and installs skill content from a mutable repository reference. Although this is not an MCP server configuration as the detector claims, it creates a supply-chain exposure: a compromised future release or repository revision could execute code or introduce malicious agent instructions when a user installs it.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The inline installation command leaves both the npm CLI version and the downloaded skill revision unspecified. This is a CLI installation rather than an MCP server reference, but mutable upstream content could introduce code execution or malicious agent instructions if an upstream account or release is compromised.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The prominent one-command installation executes an unpinned npm CLI and retrieves a skill without an immutable revision. The detector incorrectly calls this an MCP server, but the underlying supply-chain risk is real and depends on upstream compromise or an unsafe future update, not on demonstrated malicious content here.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The usage section repeats an installation command with no fixed CLI version or skill revision. Although it does not configure an MCP server, following it can execute changed upstream CLI code and install changed agent instructions without a reproducible review boundary.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The inline installation command invokes a version-unspecified npm CLI and references mutable skill content. This is not an MCP server declaration, but compromised upstream updates could execute code or install adversarial instructions into the user's agent environment.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The one-command installation does not pin either the executable CLI package or the downloaded skill revision. The MCP-specific label is inaccurate, but the command exposes installers to unreviewed upstream changes if a dependency or repository is compromised.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The usage example repeats the unpinned CLI execution and mutable skill installation. While no malicious behavior is shown and this is not an MCP configuration, an upstream compromise could change what code runs or what instructions the installed agent trusts.

Content

No source excerpt is available for this finding.

The supposedly observation-only report includes architectural recommendations and a prompt-health benchmark.

Low
Category
Excessive Agency
Confidence
94% confidence
Finding

The module documentation at L005–L006 promises observation without judgment, and L157 repeats that the report contains only observed facts and no diagnostic judgments. However, L187–L200 recommends where prompt content belongs (Wiki/Memory, Skill, Code/Validator, or Prompt) and introduces a ≥70% 'healthy' benchmark, which are normative assessments rather than objective observations.

Content

No source excerpt is available for this finding.