Skills
Navigate
skills/drshailesh88/integrated_content_os/content-seo-optimizer/Gen Agent Trust Hub

content-seo-optimizer

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it scrapes external web content and incorporates it into the prompt sent to the LLM for analysis.
  • Ingestion points: The scrape_page function in scripts/seo_audit.py fetches data from arbitrary URLs provided via the --url argument.
  • Boundary markers: The generate_audit_prompt function in scripts/seo_audit.py interpolates scraped data (title, meta description, H1, headings, and word count) directly into the system prompt without explicit delimiters or warnings to ignore embedded instructions.
  • Capability inventory: The skill possesses network access (via the requests library) and the ability to write files to the local file system (via save_report in scripts/seo_audit.py).
  • Sanitization: Content is partially cleaned of script, style, nav, footer, and header tags using BeautifulSoup, but the resulting text is not sanitized against adversarial prompt instructions hidden in the body or metadata of the target page.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 12:15 PM