The Agent Skills Directory

[SAFE]: The skill is configured with allowed-tools: Read, which restricts its capabilities to only reading file content. This prevents the agent from executing arbitrary commands, writing to the filesystem, or performing network operations.
[SAFE]: References to external documentation point to on.cypress.io, which is the official and authoritative domain for the skill author's own product. These references are used solely for informational purposes.
[SAFE]: While the skill analyzes user-provided test files (an ingestion surface for untrusted data), the risk of indirect prompt injection is mitigated by the lack of high-privilege tools. The agent's instructions focus on structured analysis and explanation rather than executing the contents of the files it reads.

cypress-explain