page-seo-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches and parses full HTML content from external, user-provided URLs to perform its analysis. This creates a surface for indirect prompt injection where an attacker could place hidden instructions within a webpage to influence the agent's SEO report or recommendations.
- Ingestion points: The skill retrieves external content in Step 2 ("Fetch and parse page") of the process described in
SKILL.md. - Boundary markers: No specific boundary markers or instructions to ignore embedded commands are defined to separate the untrusted web content from the agent's instructional logic.
- Capability inventory: The skill utilizes several scripts (
tech-seo-auditor.py,content-scorer.py,schema-generator.py,competitor-scraper.py) to process the external data and generates actionable recommendations and JSON-LD code. - Sanitization: There are no explicit instructions for sanitizing or filtering the HTML content before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill's core functionality involves connecting to and downloading content from arbitrary external URLs provided by the user. While essential for the tool's purpose, this represents routine network interaction with untrusted external hosts.
Audit Metadata