graphql-architect
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- PROMPT_INJECTION (SAFE): The instructions are focused on GraphQL design and optimization. There are no attempts to bypass safety filters, extract system prompts, or override agent constraints.
- DATA_EXFILTRATION (SAFE): No commands or instructions for network access or reading sensitive local files were found.
- EXTERNAL_DOWNLOADS (SAFE): No external dependencies or remote script downloads are specified.
- COMMAND_EXECUTION (SAFE): There are no shell commands, script executions, or subprocess calls defined in the skill.
- CREDENTIALS_UNSAFE (SAFE): No hardcoded secrets, API keys, or private tokens are present in the metadata or body.
- INDIRECT_PROMPT_INJECTION (SAFE): While the skill is designed to process user-provided GraphQL requirements, it lacks any automated tool execution capabilities that would create a high-risk attack surface.
Audit Metadata