dmr-from-django-ninja
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting and analyzing untrusted external data in the form of existing Django project source code.
- Ingestion points: The skill reads project API entrypoints, URL wiring, and schemas to build a migration matrix (SKILL.md).
- Boundary markers: There are no explicit instructions to the agent to treat the source code as data only or to ignore embedded instructions within that code.
- Capability inventory: The agent is authorized to modify project files, write new DTOs/Controllers, and execute CI/test commands.
- Sanitization: The instructions do not specify any sanitization or validation of the input source code before processing, creating a vulnerability where malicious comments or strings in the source code could influence the agent's code generation logic.
- [COMMAND_EXECUTION]: The workflow explicitly requires the agent to execute shell commands, specifically repository-native CI entrypoints and test suites (e.g., pytest or Docker-based tests), to validate migration slices. This is a functional requirement of the skill's purpose but involves the execution of commands derived from the project's environment.
Audit Metadata