python-development-python-scaffold

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes untrusted input to generate project structures.\n
  • Ingestion points: User requirements and project metadata enter the agent context through the $ARGUMENTS placeholder in SKILL.md.\n
  • Boundary markers: Absent; the skill lacks delimiters or specific instructions to the agent to ignore potentially malicious instructions embedded within user input.\n
  • Capability inventory: The skill instructions include executing shell commands (uv, git, django-admin) and performing file system writes (creating project structures, writing pyproject.toml and .env.example).\n
  • Sanitization: Absent; there is no logic provided within the skill to sanitize or escape user-provided strings before they are interpolated into commands or file content.\n- [COMMAND_EXECUTION]: The skill directs the agent to perform shell operations for project initialization, such as uv init and git init. While these are standard development workflows, the use of user-supplied variables (like project names) in these commands requires the agent to implement its own security boundaries to prevent shell command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 06:51 AM