seo-local

Pass

Audited by Gen Agent Trust Hub on Oct 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze content from external web pages, which is an untrusted data source. \n
  • Ingestion points: scripts/fetch_page.py is used to fetch raw HTML and robots.txt files from external URLs. \n
  • Boundary markers: The SKILL.md file and references/skill-contract.md contain specific directives to treat scraped material as untrusted and not to follow instructions found within that data. \n
  • Capability inventory: The skill can write files to the local environment (e.g., markdown and PDF reports) and perform network requests. \n
  • Sanitization: scripts/fetch_page.py performs basic metadata extraction using regex and standard HTML unescaping. The scripts/schema_generator.py script uses JSON-safe escaping when interpolating user-provided values into templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 19, 2026, 06:48 PM