Back to Prompt Library
planning

Define Security Agent

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Design Security Audit Agent Teams with OpenAI Agents SDK and E2B

Format
Text-first
Lines
1
Sections
1
Linked challenge
Design Security Audit Agent Teams with OpenAI Agents SDK and E2B

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Initialize an Agent using OpenAI Agents SDK, assigning it a system prompt for static code analysis using Claude Opus 4.6.6 capabilities.

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Preserve the role framing, objective, and reporting structure so comparison runs stay coherent.

Tune next

Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.

Verify after

Check whether the prompt asks for the right evidence, confidence signal, and escalation path.