Back to skill

Security audit

Skill Search Optimizer

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a search-optimization guide, but it tells users to run mutable npm CLI commands and install competing skills without review safeguards.

Treat this as a review-needed skill. Before following its commands, pin and verify the molthub CLI version, inspect any competitor skill before installing it, use a sandbox with minimal filesystem and environment access, and check local skill contents for secrets before publishing.

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
SKILL.md:293
Finding

Unpinned CLI Execution and Unreviewed Third-Party Skill Installation

Content
View full analysis

Vulnerability Details

File Location: SKILL.md:293-299
Vulnerability Type: Supply-chain risk from an unpinned npm CLI and third-party skill installation
Risk Level: Medium

Vulnerable Code

bash
# Find skills in your category
npx molthub@latest search "your topic"

# For each competing skill:
# 1. Install it
npx molthub@latest install competitor-skill

The same unpinned npx molthub@latest pattern is also used for search and publishing operations at SKILL.md:56, SKILL.md:229-244, and SKILL.md:270-286.

Technical Analysis

The documented workflow uses npx to retrieve and execute the package version currently associated with the mutable latest distribution tag. No fixed version, package integrity value, lockfile, or provenance-verification procedure is specified. Consequently, the code executed by users can change after this skill has been reviewed.

The competitor-analysis procedure compounds this risk by directing users to install an unspecified third-party skill. The instructions do not require source inspection, publisher verification, signature validation, or sandboxing before installation.

This is an insecure dependency and supply-chain practice rather than evidence that the current package itself contains a malicious payload. Exploitation would depend on compromise or malicious control of the npm package, one of its dependencies, the relevant registry account, or the selected competitor skill.

Attack Path

  1. An attacker compromises the molthub package, its publisher account, or a transitive dependency, and causes a malicious release to receive the latest tag; alternatively, the attacker publishes a malicious competitor skill.
  2. A user follows the documented command using npx molthub@latest.
  3. npx retrieves and runs the package version selected at execution time rather than a previously reviewed, pinned version.
  4. The compromised CLI runs with the privileges ...[truncated 955 chars]
Remediation
View remediation

Remediation Suggestions

  1. Replace npx molthub@latest with an explicitly pinned and reviewed version, for example npx molthub@X.Y.Z, after verifying the official package identity.
  2. Prefer a project-local dependency managed through a lockfile so the exact package and transitive dependency versions are reproducible.
  3. Verify npm package provenance, publisher identity, signatures or attestations where available, and registry integrity metadata before execution.
  4. Review release notes and source changes before updating the pinned CLI version.
  5. Require source inspection of competitor skills before installation, including their scripts, lifecycle hooks, dependencies, and requested capabilities.
  6. Install and evaluate untrusted skills in an isolated container or sandbox with minimal filesystem access, no sensitive environment variables, restricted network access, and a non-privileged user.
  7. Disable dependency lifecycle scripts during inspection where feasible and only enable them after review.
  8. Add an explicit warning that publishing transmits selected local skill content to an external registry and require users to check it for secrets before upload.
Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (20)

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · SKILL.md (reported line 278)May include surrounding context.

md
npx molthub@latest search "secondary query"

# 3. If ranking is poor, update the description
# Edit SKILL.md frontmatter

# 4. Publish updated version
npx molthub@latest publish ./skills/my-skill \

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% 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 · SKILL.md (reported line 302)May include surrounding context.

md
npx molthub@latest install competitor-skill

# 2. Read the description
head -10 skills/competitor-skill/SKILL.md

# 3. Compare:
#    - Does their description cover queries yours doesn't?

Static analysis

No suspicious patterns detected.