python-debugpy

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the debugpy package if not present. This package is maintained by Microsoft and is a standard tool for Python debugging.\n- [COMMAND_EXECUTION]: Uses shell commands to invoke the Python interpreter for debugging sessions with pdb and debugpy. These operations are consistent with the skill's purpose.\n- [SAFE]: The skill enforces security best practices by recommending that debug servers bind to 127.0.0.1 and explicitly warns against attaching to security-sensitive or production processes without approval.\n- [PROMPT_INJECTION]: Provides an attack surface for indirect prompt injection as it processes and debugs Python code. (1) Ingestion points: local scripts and modules specified in commands; (2) Boundary markers: absent; (3) Capability: full interactive debugging REPL; (4) Sanitization: absent. This risk is inherent to debugging tools and managed by user oversight of the code being debugged.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 01:13 AM
Security Audit — agent-trust-hub — python-debugpy