Security audit

Pop-Up Shop Planner

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown planning guide for pop-up shops, with no executable behavior, but users should add privacy and consent controls before using its customer data capture advice.

Install/use is reasonable for planning, but do not treat its marketing sections as compliance-ready. Before collecting emails, SMS numbers, visitor behavior, photos, or retargeting audiences, require clear opt-in where applicable, privacy notice language, unsubscribe/opt-out handling, limited retention, and review of local privacy, SMS, email, ad-platform, and venue rules.

A.I.G

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

SkillSpector

Vulnerability Patterns

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

Findings (5)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill explicitly encourages collecting email/SMS data at checkout and using it for later marketing without instructing the user to obtain informed consent, provide privacy notice disclosures, or comply with applicable laws such as CAN-SPAM, TCPA, GDPR, or CCPA. In a retail-planning context, this omission can directly lead operators to gather and reuse personal data unlawfully, especially for SMS marketing and behavioral targeting.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The post-event plan recommends segmented follow-up and retargeting based on visitor behavior, but it does not mention consent, lawful basis, notice, or opt-out requirements for using captured visitor data in targeted marketing. Because this workflow operationalizes profiling and remarketing after an in-person event, it increases the chance that users will misuse personal data in ways that violate privacy and communications regulations.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The template explicitly plans collection of email/SMS captures as a success metric but provides no guidance to obtain informed consent, present required disclosures, or handle personal data lawfully. In a retail marketing context, this omission can lead users to implement signup flows that violate privacy, telemarketing, or data protection requirements.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The post-event plan includes retargeting visitors who did not purchase, but the template omits any reminder that retargeting usually depends on tracking technologies, audience matching, or prior consent under applicable privacy laws. This can encourage deployment of ad pixels or use of captured visitor data for remarketing without proper notice or permission.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: This markdown file recommends obtaining foot traffic data from a landlord, using Placer.ai, and counting passersby, but it does not include any user-facing caution about privacy expectations, platform terms, or responsible handling of location-derived data. Because SQP-2 applies to markdown files when descriptions omit warnings about behaviors that could affect privacy, this is a mild but valid omission.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.