The Agent Skills Directory

[SAFE]: The skill follows best practice for a developer tool, using canonical documentation sources and a structured audit/build workflow. No malicious code, exfiltration patterns, or obfuscation were detected.
[INDIRECT_PROMPT_INJECTION]: The skill processes external documentation to guide its actions, which is a standard functional requirement for this type of assistant.
Ingestion points: External documentation files such as js/overview.md accessed via the read_genkit_docs tool.
Boundary markers: Not explicitly defined in the skill instructions.
Capability inventory: The skill has the capability to generate code and verification tests as part of the build workflow.
Sanitization: The skill relies on the canonical nature of the documentation sources.

genkit-core-js