Security audit

Small Engine Repair

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward small-engine repair guide, with a disclosed but unpinned install command users should treat cautiously.

Review the install path before use, especially in privileged or credential-rich environments. Prefer a pinned or otherwise trusted ClawHub installer when available; the repair guidance itself is coherent and limited to small-engine troubleshooting.

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: SKILL.md:15
Finding: Unpinned Package Execution Through npx
Content: View full analysis
Remediation: View remediation
install small-engine-repair" ``` 2. Verify the selected release against the package publisher's trusted documentation, provenance, and registry integrity metadata before adoption. 3. Use a lockfile or an equivalent immutable dependency manifest where the installation framework supports one. 4. Prefer a trusted internal registry or package mirror with allowlisting and retention controls for audited artifacts. 5. Enforce package signatures, provenance attestations, or cryptographic checksum verification where supported. 6. Run installation in a sandbox or least-privileged account without production credentials, sensitive environment variables, or unnecessary filesystem access. 7. Review updates explicitly and repeat the security audit before changing the pinned version. 8. Avoid relying on a mutable package tag such as `latest`, including implicitly through an omitted version. ]]>

SkillSpector

Vulnerability Patterns

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Rp1

Medium

Category: MCP Rug Pull
Confidence: 93% confidence
Finding: The skill metadata instructs installation via npx clawhub install small-engine-repair without pinning a specific version or immutable package reference. This creates a supply-chain risk: a later malicious or compromised release of the CLI or dependency chain could be fetched and executed at install time, and npx commonly executes remote package code immediately.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.