qa-contract-api

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external API specifications (OpenAPI, GraphQL, AsyncAPI) and Pact contract files which act as untrusted ingestion points. These inputs are used to drive testing logic and generate report findings.
  • Ingestion points: External configuration files such as openapi.yaml, openapi.json, asyncapi.yaml, and pacts/*.json (local or remote URLs).
  • Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded natural language commands within the processed specifications.
  • Capability inventory: The skill utilizes Bash for command execution (running CLI tools like Schemathesis) and Read for file system access.
  • Sanitization: Absent; the skill does not explicitly mention sanitization or validation of the content of the specifications beyond schema conformance.
  • [COMMAND_EXECUTION]: The skill instructions involve executing various CLI tools via Bash, including schemathesis, pact-verifier, oasdiff, and openapi-diff. These tools are used for their intended purpose of API validation and schema diffing.
  • [EXTERNAL_DOWNLOADS]: The skill references and encourages the use of established open-source tools and documentation from well-known platforms including the OpenAPI Initiative, Pact Foundation, Schemathesis, and The Guild (GraphQL Inspector). These references are documented neutrally as they are industry-standard resources for API testing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 09:28 AM