wise-mcp

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation from external sources to ensure it has the latest information before generating code.
  • Evidence: Fetches documentation from https://gofastmcp.com/llms-full.txt and https://www.arcade.dev/patterns/llm.txt.
  • [PROMPT_INJECTION]: The skill presents an Indirect Prompt Injection surface (Category 8) by directing the agent to read and follow instructions from external, developer-controlled websites during its workflow.
  • Ingestion points: Documentation URLs provided in SKILL.md (gofastmcp.com, arcade.dev).
  • Boundary markers: None identified; the agent is encouraged to treat the fetched content as primary guidance.
  • Capability inventory: The agent is tasked with writing Python code, defining tool schemas, and structuring server logic.
  • Sanitization: None; the agent consumes the raw text content directly into its context to inform code generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:07 AM