The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard development commands such as npx sanity for schema management and document operations, as well as npm run for local seeding scripts.
[DATA_EXPOSURE]: The skill references a specific Sanity project ID (namias-cms) which aligns with the author's identity (PP-Namias). It correctly uses placeholders like <token> and <SANITY_REVALIDATE_SECRET> for sensitive credentials, avoiding hardcoded secrets.
[EXTERNAL_DOWNLOADS]: The skill includes curl commands targeting namias-cms.api.sanity.io. This is the official API endpoint for Sanity.io, a well-known service, and the project ID matches the vendor's namespace.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data from a CMS, creating a potential attack surface.
Ingestion points: Data is retrieved from the Sanity API via curl commands in SKILL.md.
Boundary markers: No specific delimiters or safety instructions are defined for the retrieved content.
Capability inventory: The skill performs command execution (npx sanity), network requests (curl), and assumes the ability to edit local schema files.
Sanitization: No explicit sanitization or validation of the remote CMS content is mentioned.

sanity-data-operations