bootstrap-python-mcp-service

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The shell script scripts/init_fastmcp_service.sh dynamically generates Python source files and executes them via uv run during project validation.
  • [COMMAND_EXECUTION]: The Python script scripts/assess_api_for_mcp.py utilizes importlib.import_module() to dynamically load and inspect FastAPI applications to generate mapping guidance.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection via the scripts/assess_api_for_mcp.py tool. 1. Ingestion points: The script reads and processes untrusted OpenAPI specification files and FastAPI modules. 2. Boundary markers: Absent; extracted metadata like endpoint summaries are rendered directly into the generated markdown report. 3. Capability inventory: The skill can execute arbitrary shell commands via uv and git, and write files to the local filesystem. 4. Sanitization: No sanitization is performed on the data extracted from API definitions before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 11:57 PM