seo-audit
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill processes up to 500 pages of external website content, creating a large attack surface for indirect prompt injection.
- Ingestion points: External HTML content retrieved via
scripts/fetch_page.pyand subsequent crawling of internal links. - Boundary markers: None identified. The instructions do not specify delimiters or warnings for the agent to ignore instructions found within the crawled content.
- Capability inventory: Local script execution (
scripts/fetch_page.py), file system write access (creating reports and action plans), and potential headless browser execution (Playwright for screenshots). - Sanitization: No sanitization or filtering of the crawled HTML content is described before it is analyzed by the agent or its subagents.
- [Command Execution] (LOW): The skill workflow explicitly relies on executing a local script (
scripts/fetch_page.py) and potentially Playwright. While the script content was not provided for analysis, the pattern of executing local scripts is inherent to the skill's function.
Audit Metadata