api-tests

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs verified industry-standard testing libraries including Pact, AJV, Zod, and OpenAPI validation tools from official public registries (NPM and PyPI).
  • [COMMAND_EXECUTION]: Utilizes Bash tools for environment inspection and configuration tasks, including package manager operations and project file scanning with jq, find, and grep.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes user-controlled project files like OpenAPI specifications.
  • Ingestion points: Reads content from package.json, pyproject.toml, and openapi.yaml to detect project infrastructure.
  • Boundary markers: Content from these files is processed without explicit delimiters or instructions to ignore embedded instructions.
  • Capability inventory: The skill has extensive file system access (Read, Write, Edit) and command execution (Bash) capabilities.
  • Sanitization: No explicit validation or sanitization of project file content is performed before the agent processes it for reporting or configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 08:12 PM