ai-sdk

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill fetches documentation from https://ai-sdk.dev. This is the official domain for the Vercel AI SDK and is considered a trusted source.
  • [COMMAND_EXECUTION] (SAFE): The agent is instructed to use grep and glob to search within the node_modules/ai directory. These are standard search operations for a developer tool and do not involve privilege escalation or dangerous parameters.
  • [INDIRECT_PROMPT_INJECTION] (SAFE): The skill ingests external data by fetching documentation files. While this is an attack surface, the risk is negligible due to the trusted nature of the source.
  • Ingestion points: Documentation fetched from ai-sdk.dev via HTTPS.
  • Boundary markers: Absent.
  • Capability inventory: Local file search (grep, glob).
  • Sanitization: Absent (source is a trusted official repository).
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 02:39 AM