seo-maps

Pass

Audited by Gen Agent Trust Hub on Oct 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill includes functionality to crawl external web pages, which presents a surface for indirect prompt injection.
  • Ingestion points: scripts/fetch_page.py retrieves content from user-provided URLs.
  • Boundary markers: Both SKILL.md and references/skill-contract.md explicitly instruct the agent to treat external content as untrusted evidence and to ignore any instructions embedded within it.
  • Capability inventory: The skill possesses network access via scripts/fetch_page.py and file-writing capabilities through scripts like scripts/generate_markdown_report.py.
  • Sanitization: scripts/fetch_page.py mitigates SSRF risks by validating that target URLs do not resolve to private or reserved IP addresses.
  • [EXTERNAL_DOWNLOADS]: The scripts/generate_pdf_report.py script identifies reportlab as an optional dependency for PDF rendering and instructs the user on how to install it manually. This is a standard practice for optional features and does not involve automated or hidden installations.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 20, 2026, 06:33 AM