django-query-profiling
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data including APM traces, database slow-query logs, and HTTP request parameters to diagnose performance issues.
- Ingestion points: External evidence enters the agent context through APM transaction traces, database logs, and captured request parameters as described in SKILL.md and references/tooling-and-reproduction.md.
- Boundary markers: The instructions do not provide specific boundary markers or warnings to the agent to ignore potentially malicious instructions embedded within the analyzed data.
- Capability inventory: The skill facilitates searching local source code, inspecting view and serializer logic, and executing Python snippets for performance reproduction.
- Sanitization: There is no evidence of sanitization, validation, or escaping of the ingested external content before it is processed.
Audit Metadata