Skills
Navigate
skills/integromat/make-skills/make-functions-v2/Gen Agent Trust Hub

make-functions-v2

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill facilitates the authoring, testing, and execution of TypeScript source code via the Make platform's official tools. It utilizes functionality such as function_run_create_inline for direct execution of source candidates and function_run_create for executing published versions.
  • [INDIRECT_PROMPT_INJECTION]: The skill handles untrusted external data, specifically function source code and execution results, which represents a potential attack surface.
  • Ingestion points: Remote resource retrieval occurs via function_version_get and function_run_get (SKILL.md).
  • Boundary markers: The skill contains explicit instructions for the agent to treat all returned source code and execution outputs as data rather than instructions (SKILL.md, Ground rules).
  • Capability inventory: The available tools allow for the creation, modification, execution, and deletion of code resources on the Make platform.
  • Sanitization: The instructions mandate the use of JSON Schema for input and output contracts to validate and scope data processed by the functions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 03:26 PM