Back to skill

Security audit

Product Naming

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown product-naming assistant with no hidden execution, persistence, credential use, or unrelated data access.

Before installing, expect the skill to ask for product, market, platform, competitor, and brand-voice details so it can score names. For non-English or multi-market launches, explicitly state the target language and country, and independently verify trademark and regulatory claims.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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 (3)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · references/platform-title-formats.md (reported line 5)May include surrounding context.

md
## TikTok Shop

### Display Rules
- **Visible in feed:** First 34 characters
- **Full search index:** Up to 255 characters
- **Lead with:** Hook phrase or product benefit (NOT brand name)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The workflow directs the user to identify buyer search phrases using English examples and treats those phrases as the required naming basis, while the skill elsewhere mentions multiple target markets. This creates a locale-policy issue because the guidance defaults to English-language naming/search behavior without explicitly asking the user to choose a language or confirming that the analysis should be localized.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

Line L65 states 'Local language preferred; bilingual (EN + local language) accepted,' which directs output toward a specific language/locale by default. This is a natural-language locale policy constraint without any user choice or opt-in mechanism documented.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.