fastmcp
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructions advise agents to 'Display the
outputfield content verbatim', which establishes an attack surface for indirect prompt injection if external data retrieved from APIs contains malicious instructions. - Ingestion points: Data is ingested via
httpxGET requests in example tools likeget_recordandlist_recordsinSKILL.md. - Boundary markers: The provided code examples and instructions do not demonstrate the use of delimiters (e.g., XML or Markdown blocks) to isolate untrusted content from the rest of the agent's context.
- Capability inventory: The skill examples utilize network operations (
httpx) and access environment variables (os.environ). - Sanitization: There is no evidence of content validation or escaping of remote data before it is interpolated into the formatted output returned to the agent.
Audit Metadata