seo-sitemap
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and analyze external XML sitemap data provided by users or fetched from URLs.
- Ingestion points: External XML sitemap files and URLs processed during the 'Analyze Existing Sitemap' mode.
- Boundary markers: The instructions lack explicit directives for the agent to treat the content of the XML tags strictly as data or to ignore any natural language instructions that might be embedded within the XML fields.
- Capability inventory: The agent is instructed to parse XML structures, validate formatting, and perform network requests to verify HTTP 200 status for all contained URLs.
- Sanitization: There is no mention of sanitizing or filtering the content of the sitemap tags (e.g.,
<loc>,<lastmod>) to prevent the agent from executing instructions hidden within those fields.
Audit Metadata