agent-friendly-apis

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • External Content Retrieval: The skill is designed to fetch lesson content, curriculum indexes, and search results from the official vercel.com domain. This behavior is expected for a companion tool meant to drive a student through an online course.
  • File System Interaction: To provide context-aware tutoring and verify lesson completion, the skill reads the local project's directory structure and file contents (such as app/api/ and lib/data.ts). This access is necessary for the skill's primary purpose of progress detection and evaluation.
  • Indirect Prompt Injection Surface: The skill processes untrusted data in the form of the student's local codebase to generate documentation and provide feedback. While this creates a theoretical surface for instructions embedded in code to influence the agent, the risk is minimized by the skill's specific focus on API structure and documentation patterns, and it is a standard characteristic of code-analysis tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 01:24 AM