neon-drizzle-setup
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- EXTERNAL_DOWNLOADS (LOW): The skill provides instructions to fetch data using
curlfromhttps://fullstackrecipes.com. This domain is not part of the trusted external sources list, posing a risk of ingesting unverified content. - PROMPT_INJECTION (LOW): The skill implements an indirect prompt injection surface by fetching external 'recipes' to be processed by the agent.
- Ingestion points: The
curlcommand inSKILL.mdfetches content from an external API. - Boundary markers: Absent; there are no delimiters or instructions to treat the fetched content as untrusted data.
- Capability inventory: The agent is expected to use the fetched recipe to perform complex setup tasks, including code generation and database configuration.
- Sanitization: None; the skill does not suggest any validation or sanitization of the fetched content.
Audit Metadata