django-perf-review
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: This skill is designed to ingest and interpret external, untrusted Django source code. This introduces a surface for indirect prompt injection where malicious instructions embedded in the code (such as in comments or strings) could influence the agent's behavior.
- Ingestion points: Uses
Read,Grep, andGlobtools to retrieve file contents from a project. - Boundary markers: The instructions contain no explicit directions to treat the ingested code as data only or to ignore any natural language instructions found within it.
- Capability inventory: The skill retains access to powerful shell-execution tools including
BashandTask. - Sanitization: There is no evidence of filtering or sanitizing the content of the files before they are processed by the AI model.
Audit Metadata