krawlup-mcp
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from external websites during SEO and AEO audits, creating a surface for indirect prompt injection.
- Ingestion points: Untrusted website content is retrieved through tools such as
get_site_report,get_insights, andget_website_analytics. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the retrieved website data.
- Capability inventory: The agent can use audit data to propose site modifications and manage product catalog listings via the krawlup API.
- Sanitization: No sanitization or filtering of the external website data is described in the tool definitions.
- [EXTERNAL_DOWNLOADS]: The skill connects to the vendor's API at
https://api.krawlup.com/mcpto perform its primary functions.
Audit Metadata