skills/sharanharsoor/skills/fastmcp/Gen Agent Trust Hub

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 output field 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 httpx GET requests in example tools like get_record and list_records in SKILL.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
Risk Level
SAFE
Analyzed
Jun 25, 2026, 12:00 AM
Security Audit — agent-trust-hub — fastmcp