Back to skill

Security audit

Shopify Product Promo

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently uses Revid to turn a public product URL into a promo video, with no hidden persistence or unrelated local access found.

Install only if you are comfortable sending public product-page URLs and extracted product details to Revid using your REVID_API_KEY. Avoid private storefront, unpublished, customer-specific, or internal URLs unless you have confirmed they may be shared with that service; adjust language/voice defaults when needed.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding

The skill includes shell-based execution examples and operational steps but does not declare any tool restrictions or allowed tool scope. In agent environments, that mismatch can lead to over-broad execution capability, making it easier for an agent to invoke shell/network actions without explicit least-privilege boundaries.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill tells the agent to send a user-supplied product URL to Revid for scraping and video generation, but it does not clearly warn the user that the external service will receive the URL and extracted page contents. This creates a transparency and data-handling risk, especially if users provide non-public, sensitive, or internal storefront links by mistake.

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's sample payload fixes the voice language to en-US, which can force a specific language/locale outcome. The file does not mention that users may choose another language or that English is an optional default, so it violates the language/locale choice policy.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

The example performs an external API call to www.revid.ai and includes the user-provided product URL in the request, causing data to leave the local trust boundary. In the context of an agent skill, this is security-relevant because it operationalizes transmission of user-supplied data and potentially scraped page contents to a third party.

Content

Scanner excerpt · SKILL.md (reported line 101)May include surrounding context.

bash
URL="https://your-shop.myshopify.com/products/your-product"

curl -s https://www.revid.ai/api/public/v3/render \
  -H "Content-Type: application/json" \
  -H "key: $REVID_API_KEY" \
  -d "$(jq --arg url "$URL" '.source.url=$url' \

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · examples/run.sh (reported line 13)May include surrounding context.

sh
PAYLOAD="$(jq --arg url "$URL" '.source.url=$url' "$HERE/shopify-aeropods.json")"

echo "→ POST /render"
RESP=$(curl -fsS https://www.revid.ai/api/public/v3/render \
  -H "Content-Type: application/json" \
  -H "key: $REVID_API_KEY" \
  -d "$PAYLOAD")

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest sets the voice language explicitly to "en-US", which is a natural-language locale restriction. There is no indication in this file that the user can opt into a different language or that the skill is intentionally limited to a specific region or compliance context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.