ai-sdk
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use
grepandglobutilities to search for documentation and source code within the localnode_modulesdirectory. - [EXTERNAL_DOWNLOADS]: The skill fetches search results and markdown documentation from the official and trusted
ai-sdk.devdomain. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external documentation and local library files which could technically contain instructions.
- Ingestion points: Local files in
node_modules/ai/and remote markdown files fromhttps://ai-sdk.dev/docs/. - Boundary markers: Not explicitly defined.
- Capability inventory: Uses file system search (
grep,glob) and network requests to retrieve data. - Sanitization: Relies on the agent's native handling of documentation content; the sources are well-known and official.
Audit Metadata