schemathesis

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the schemathesis library via pip, a standard practice for Python development.- [COMMAND_EXECUTION]: The instructions demonstrate using the st command-line interface to execute API tests and fuzzing operations against target endpoints.- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it processes external OpenAPI and GraphQL schemas which are untrusted data. * Ingestion points: Schemas loaded from URLs via st run and schemathesis.from_url in SKILL.md. * Boundary markers: The instructions do not define specific delimiters for the schema content to separate it from the agent's internal reasoning. * Capability inventory: The agent has the ability to make network requests (for fuzzing) and write files (for test reports). * Sanitization: The Schemathesis library provides structural parsing and validation of schema documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 09:09 PM
Security Audit — agent-trust-hub — schemathesis