django-models
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by instructing the agent to ingest external data from project context files.\n
- Ingestion points: Reads
.agents/django-project-context.mdand.claude/django-project-context.mdas specified inSKILL.md.\n - Boundary markers: Absent; there are no instructions to delimit or ignore instructions within these context files.\n
- Capability inventory: No executable scripts are included in the skill; the skill body provides instructions for the agent to generate and present shell commands and Python code for model definition.\n
- Sanitization: Absent; no validation or filtering is specified for the ingested context data.\n- [COMMAND_EXECUTION]: The skill documents standard Django management commands such as
makemigrations,migrate, andsqlmigrate. These are intended for manual project administration and are not executed automatically by the skill.\n- [NO_CODE]: The skill consists entirely of Markdown documentation and reference materials, without any executable scripts, binary files, or automated installation processes.
Audit Metadata