The Agent Skills Directory

[COMMAND_EXECUTION] (LOW): The skill utilizes shell commands including curl, jq, grep, and npx to fetch model lists, search local documentation in node_modules, and launch development tools. These operations are consistent with the skill's primary purpose of supporting AI SDK development.
[EXTERNAL_DOWNLOADS] (LOW): The skill performs network requests to https://ai-gateway.vercel.sh and https://ai-sdk.dev to retrieve current API metadata and documentation. It also recommends installing packages from the @ai-sdk scope. These targets are recognized as trusted external sources associated with Vercel.
[DATA_EXFILTRATION] (SAFE): No patterns of sensitive data exposure or exfiltration were detected. Network operations are focused on retrieving public information and do not involve sensitive local files like SSH keys or environment secrets.
[INDIRECT_PROMPT_INJECTION] (LOW): The skill possesses a vulnerability surface by ingesting external data from documentation APIs and local library files while having shell execution capabilities. However, the risk is mitigated by the trusted nature of the sources.
Ingestion points: node_modules/ai/docs/, https://ai-sdk.dev/api/search-docs.
Boundary markers: Absent.
Capability inventory: curl, jq, grep, pnpm, npx.
Sanitization: Absent.

ai-sdk