seo-drift
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted content (titles, headings, meta tags, and JSON-LD schema) from user-provided URLs. This creates a surface for indirect prompt injection where an attacker could embed malicious instructions in webpage metadata that the agent later interprets as instructions during the comparison or reporting phase.
- Ingestion points: Page content fetched from user-provided
<url>withinscripts/fetch_page.pyandscripts/parse_html.py. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined when processing the parsed SEO elements.
- Capability inventory: The skill executes local scripts for parsing and comparison and offers to generate HTML reports from the data.
- Sanitization: The skill explicitly implements SSRF protection using
google_auth.validate_url()to block private IPs and reserved ranges, which is a strong positive security control.
Audit Metadata