django-db-performance
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill establishes a professional workflow for database performance diagnosis. It leverages standard Django mechanisms like QuerySet.explain() and connection.queries without introducing external scripts, executable binaries, or unauthorized network operations.
- [PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection as it instructs the agent to ingest untrusted application data (e.g., request parameters, SQL traces, and endpoint inputs). * Ingestion points: Documented in SKILL.md (Step 1: Capture the symptom) and references/diagnostic-flow.md (Evidence Template: Inputs). * Boundary markers: No specific delimiters or safety warnings are provided for the captured data. * Capability inventory: Database inspection tools (EXPLAIN), logging, and report generation as described in SKILL.md. * Sanitization: No sanitization or validation of the input symptoms or parameters is defined in the workflow.
Audit Metadata