The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze untrusted user-provided GraphQL schemas and resolver code. While this constitutes an ingestion surface for data that could contain malicious instructions (e.g., hidden in code comments), this behavior is the core intended functionality of a security auditing skill. The instructions focus on static analysis and pattern matching to identify vulnerabilities.
[EXTERNAL_DOWNLOADS]: The skill mentions external security tools semgrep and graphql-cop. The provided instructions direct the agent to detect if these tools are already available in the execution environment rather than forcing unverified downloads or installations.

graphql