skills/jimmylv/bibigpt/ai-sdk/Gen Agent Trust Hub

ai-sdk

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill contains directives intended to override the agent's internal knowledge base, such as "Everything you know about the AI SDK is outdated or wrong" and "Never rely on memory."
  • [PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface as it is instructed to ingest and process external markdown documentation from the web. • Ingestion points: Remote markdown files from ai-sdk.dev. • Boundary markers: Absent for external documentation. • Capability inventory: Shell command execution (pnpm, curl, npx) and local file system access. • Sanitization: No sanitization or validation of external content is specified.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute several shell commands for development and environment setup: pnpm add ai for package installation, grep for searching within the node_modules directory, curl for retrieving model metadata from ai-gateway.vercel.sh, and npx @ai-sdk/devtools for running development tools.
  • [EXTERNAL_DOWNLOADS]: The skill fetches model configuration and documentation from ai-gateway.vercel.sh and ai-sdk.dev. These domains are associated with Vercel's service infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 05:28 AM