The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or safety bypass attempts were detected. The skill is authored by the official vendor and adheres to security best practices by separating design guidance from live operations.
[EXTERNAL_DOWNLOADS]: The skill references official Algolia learning and documentation sites for context.
Evidence: References to academy.algolia.com and algolia.com/doc in SKILL.md.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted sample records from users to facilitate data modeling design. This behavior is safe because the skill is purely instructional and lacks the capabilities (like shell execution or network exfiltration) required to exploit such an injection.
Ingestion points: User-provided sample records requested in SKILL.md and references/data-modeling-guide.md.
Boundary markers: Absent, which is appropriate for a non-executable design skill.
Capability inventory: None. The skill does not execute commands or perform network operations.
Sanitization: None.

algolia-data-modeling