geo-schema-gen
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill performs network operations to external, non-whitelisted domains.
- The scripts
scripts/batch_generate.pyandscripts/generate_schema.pyuse therequestslibrary to fetch content from arbitrary URLs provided by the user or found in sitemaps. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting untrusted data from the web.
- Ingestion points: The scripts
scripts/batch_generate.pyandscripts/generate_schema.pyfetch and parse HTML content from external websites. - Boundary markers: Absent. The scripts extract text directly from HTML elements (like
<h1>,<title>, and<meta>tags) and place them into structured JSON fields without delimiters or "ignore" instructions. - Capability inventory: The skill has network-read capabilities and writes the generated JSON-LD files to the local file system.
- Sanitization: Absent. There is no validation or sanitization of the strings extracted from external web pages before they are returned to the agent context.
Audit Metadata