dmr-from-dj-rest-auth
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves reading and analyzing existing project source code to perform the migration, which creates a potential surface for indirect prompt injection if the user's codebase contains adversarial instructions.
- Ingestion points: The agent processes local source code files including Django serializers, views, and settings files.
- Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when reading project files.
- Capability inventory: The agent is tasked with writing new code, modifying configurations, and updating authentication logic.
- Sanitization: No explicit sanitization or filtering is defined for the content extracted from the local codebase.
- [SAFE]: The skill instructions explicitly prioritize the preservation of security properties, such as ensuring HTTP-only and Secure flags are maintained on authentication cookies.
- [SAFE]: The migration guide mandates the use of Django's @sensitive_post_parameters and @sensitive_variables decorators to prevent credentials from appearing in error reports.
- [SAFE]: The skill references documentation for well-known open-source libraries and vendor-maintained resources from wemake-services.
Audit Metadata