Skills
Navigate
skills/iamwaqargulzar/marketing-agent-os/seo-content-brief/Gen Agent Trust Hub

seo-content-brief

Pass

Audited by Gen Agent Trust Hub on Oct 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external websites via the scripts/fetch_page.py tool, creating a surface for indirect prompt injection. \n
  • Ingestion points: External web pages are fetched and processed as evidence for SEO analysis. \n
  • Boundary markers: Strong instructions are present in SKILL.md and references/skill-contract.md requiring the agent to treat scraped text as untrusted and to ignore any embedded instructions. \n
  • Capability inventory: The skill can execute Python scripts, perform network requests, and write report files. \n
  • Sanitization: Content is unescaped and stripped of HTML tags, but the primary defense relies on agent-level instructional guardrails. \n- [EXTERNAL_DOWNLOADS]: The script scripts/generate_pdf_report.py references the reportlab package as an optional dependency from a well-known service (PyPI) to support PDF generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 19, 2026, 06:50 PM