moai-baas-vercel-ext

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection vulnerabilities through its data ingestion mechanisms.
  • Ingestion points: The skill uses the mcp__context7__get-library-docs tool to retrieve external documentation for Vercel and Next.js at runtime, which is then processed by the agent. It also has access to the WebFetch tool for arbitrary web requests.
  • Boundary markers: There are no explicit instructions or delimiters defined in the prompt to ensure the agent disregards instructions or malicious commands embedded within the retrieved documentation.
  • Capability inventory: The agent is granted high-privilege tools including Bash, Write, and Edit, which significantly increases the impact of a successful injection attack.
  • Sanitization: The skill lacks mechanisms to sanitize or validate the content returned from external MCP tools or web fetches before it enters the context of the language model.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:06 AM