The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and analyze untrusted GraphQL schema definitions, resolver implementations, and server configurations.
Ingestion points: The workflow identifies and processes a wide range of code files including **/*.graphql, **/schema.*, and **/resolvers/** as primary data sources.
Boundary markers: The skill's workflow for manual and automated analysis does not define specific delimiters or instructions to ignore instructions embedded within the analyzed code comments or metadata.
Capability inventory: The skill utilizes command-line execution for security scanners and performs manual interpretation of code logic, which can be influenced by malicious content in the target files.
Sanitization: No explicit sanitization or validation of the code content is performed before it is processed by the agent.
[COMMAND_EXECUTION]: The skill executes external CLI tools, specifically semgrep and graphql-cop, to perform its auditing tasks.
[DATA_EXFILTRATION]: The skill includes functionality to analyze live GraphQL endpoints using graphql-cop, which involves making network requests to potentially non-whitelisted external domains. While this is the intended primary purpose of the tool, it represents an active network operation surface.

graphql