Back to skill

Security audit

NoteGPT Page Seo Generator I18n Skill

Security checks for vulnerabilities and agentic risk

Overview

The scanners classify this skill as benign because they report no executable scripts or major risky behavior, though two findings were judged expected for its purpose and coverage is incomplete.

The verdict is benign, not risk-free. Consider the two contextual findings and note that scanning was partial because a referenced output file was missing; the scanners do not establish what that file contains.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

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 · SKILL.md (reported line 108)May include surrounding context.

md
7. **Overall principle**
   - The final output should read like an SEO page written specifically for the target language market, not a translated version of an English page. Ensure content is natural, fluent, aligned with local search habits, and possesses good SEO readability and originality.

#### Output Rules

1. **Write ALL content to a single `.md` file** — do NOT output inline in chat
2. File naming: `SEO-[keyword]-[brand]-[lang].md` (e.g. `SEO-ai-image-enhancer-YourBrand-ja.md`)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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 · references/rules.md (reported line 650)May include surrounding context.

md
- **Write to `.md` file** — do NOT output content inline in chat
- File name: `SEO-[keyword]-[brand]-[lang].md`
- All 10 columns in `| Section | Content |` table format (output in target language)
- **Output file contains ONLY the 10 content columns** — no Schema Markup, no verification report
- Clean output: no character count tails `(XXc)`, no stray `|`, no artifacts
- Content cells: plain text, no bold/italic formatting