api-testing-patterns

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and analyze untrusted external data such as OpenAPI/GraphQL specifications and source code.
  • Ingestion points: Specification files (e.g., openapi.yaml) and code blocks provided in prompts or evaluation fixtures.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' commands when processing external content.
  • Capability inventory: The skill manages task execution across multiple agents and provides patterns for network-based API testing and database queries.
  • Sanitization: There is no evidence of validation or sanitization of the content within the ingested specifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 06:40 PM