api-graphql-apollo-server
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references several standard Node.js packages for GraphQL development, including
@apollo/server,dataloader,graphql-ws, andexpress. It also fetches a metadata schema from the vendor's GitHub repository (github.com/agents-inc). These are standard dependencies for the skill's stated purpose.- [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for ingesting and processing external data via GraphQL resolver arguments and REST API responses. It mitigates injection risks by instructing the implementation of strict schema validation and response sanitization usingformatErrorandencodeURIComponentfor dynamic URL segments. - Ingestion points: Resolver arguments (
argsinSKILL.md), HTTP headers (tokeninexamples/core.md), and REST API responses (RESTDataSourceinexamples/data-sources.md). - Boundary markers: Recommends using
formatErrorto separate internal error details from client-facing messages and GraphQL schema validation to enforce input structure. - Capability inventory: Includes network operations via
RESTDataSource(fetching from external APIs) and database queries within data sources. - Sanitization: Explicitly mandates the use of
encodeURIComponenton dynamic path segments to prevent path traversal vulnerabilities.
Audit Metadata