makedsl

Pass

Audited by Gen Agent Trust Hub on May 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a technical reference and schema guide for the Make Platform DSL. It contains no executable scripts or commands that pose a direct security risk.\n- [SAFE]: Documentation regarding data operations points to the platform's official development domain (dev-make.qtech.cn). These network operations are necessary for the skill's primary function of managing platform records.\n- [INDIRECT_PROMPT_INJECTION]: The skill describes processes for ingesting data from external API responses, which presents a surface for indirect prompt injection.\n
  • Ingestion points: Responses from resource retrieval APIs described in 'references/DataAPIDesign.md'.\n
  • Boundary markers: Interactions are restricted to structured JSON formats defined in the API documentation.\n
  • Capability inventory: The documentation enables the agent to interact with external endpoints via HTTP POST and GET methods to manage records, files, and users.\n
  • Sanitization: The documentation relies on the platform's schema validation but does not detail specific agent-side sanitization of the retrieved data content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 6, 2026, 06:49 AM