ClawHub
Back to skill

Security audit

Shopify Product Writer

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only Shopify listing writer whose behavior is coherent and disclosed, with ordinary install and publishing-review cautions.

Before installing, consider using a pinned or otherwise trusted clawhub installer path. Before publishing generated listings, review all specifications, assumptions, language choices, legal claims, and any supplier-derived text for accuracy and reuse rights.

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:40
Finding

Unpinned Package Execution in Installation Instructions

Content
View full analysis
Remediation
View remediation
install tetsuakira-vk/shopify-product-writer ``` Do not use floating tags such as `latest`, caret ranges, or tilde ranges. 2. Document the expected registry and trusted package publisher so users can verify that package resolution has not been redirected to an untrusted source. 3. Where supported, publish and document a cryptographic checksum, provenance attestation, or signed release for the exact installer artifact. 4. Prefer a lockfile-backed installation workflow for automated deployments. Commit the lockfile and use deterministic installation commands such as `npm ci`. 5. Review each installer upgrade before changing the pinned version. Include upstream ownership, release provenance, dependency changes, and package lifecycle scripts in that review. 6. Advise users not to run the installation command with administrator or root privileges. Execute it in a restricted development environment with only the permissions and credentials required for installation. ]]>

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (5)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

md
You must work with whatever level of detail is given. Do not refuse to generate output because the brief is short — use your expertise to fill gaps intelligently and flag any assumptions you made at the end.

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The README instructs users to run npx clawhub install ... without pinning a specific version of the tool being fetched and executed. This creates a supply-chain risk: users may execute a newer or compromised package version than the author intended, and because this is an install command, the impact is amplified by direct code execution on the user's system.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill mandates English output when the user provides a non-English brief, without defaulting to the user's language or asking preference. This can override user intent, cause misleading output for multilingual merchants, and create safety/compliance issues if product claims, warnings, or regulated content are translated incorrectly or without consent.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 226)May include surrounding context.

md
## Final Notes

- Never generate incomplete output. If you start, finish all five sections.
- Never ask the user to approve sections mid-generation — deliver everything at once.
- If you made assumptions due to a sparse brief, list them concisely after the tags section under a `**Assumptions made:**` note.
- If the user asks for a revision, regenerate only the section(s) they request while keeping all others intact.
- Always maintain the separator line format (`━━━`) between sections for clean visual parsing.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

This markdown file includes a workflow for rewriting supplier descriptions for a Shopify store, which could affect legal/compliance obligations around copied or derived listing content. The description presents the behavior as ready to use but does not include any user-facing warning to verify ownership, licensing, or factual accuracy before publishing.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.