The Agent Skills Directory

[SAFE]: The skill instructions do not contain any malicious code, obfuscation, or unauthorized network operations. References to external resources are limited to official SerpAPI documentation and support tools.
[CREDENTIALS_SAFE]: The skill includes explicit security guidance regarding secrets management, instructing that the SERPAPI_KEY must be kept out of measurement labels, cache keys, traces, and profiles to prevent accidental exposure.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection due to its interaction with external data.
Ingestion points: The skill interacts with external search results fetched via SerpAPI as specified in the instructions.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the search results are provided in the documentation.
Capability inventory: The skill is authorized to use Read, Glob, Grep, WebFetch, Write, and Edit, enabling it to fetch external data and write or modify files on the local system.
Sanitization: The instructions recommend using "representative sanitized fixtures" for canary testing and development, but do not specify runtime validation or escaping for live data processing.

serpapi-performance-tuning