native-data-fetching
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for fetching and processing data from external API endpoints, which presents an attack surface where untrusted content could be ingested into the agent's context.
- Ingestion points: Data is fetched via the
fetchAPI inSKILL.mdandreferences/expo-router-loaders.md. - Boundary markers: The provided code snippets do not include explicit prompt boundary markers or "ignore instructions" delimiters for the ingested data.
- Capability inventory: The skill utilizes network fetching capabilities.
- Sanitization: While the documentation mentions that users should "Validate and sanitize user input," the example code for processing API responses directly parses and returns JSON without specific sanitization of the content itself.
Audit Metadata