home/roleplay/report-prompt

REPORT PROMPT

GPTClaudeGemini··1,133 copies·updated 2026-07-14
report-prompt.prompt
# REPORT_PROMPT.md

## Step 1 — Read All Sources

Read:
- `audit-workspace/findings/GROUP-A-status.json`
- `audit-workspace/findings/GROUP-B-status.json`
- `audit-workspace/findings/GROUP-C-status.json`
- `audit-workspace/findings/GROUP-D-status.json`
- `audit-workspace/progress.json` (for preflight issues and `has_git`)

## Step 2 — Merge & Deduplicate

**Same file + same lines + same check type:** keep the higher-confidence finding, add `"also_detected_by": ["CHECK-ID"]` to the merged finding.

**Same file + same lines, different check IDs** (e.g. AUTH-001 and CRYPTO-003 both flagging a hardcoded key): merge into one finding, list both check IDs, include both remediation angles.

**Same pattern in multiple files:** keep as separate findings. Note: *"repeated pattern — also at {locations}."*

## Step 3 — Write the Report

Write to `audit-workspace/output/report.md`:

fill the variables

This prompt has 1 variable. Pro fills them into a ready-to-paste prompt for you — no manual find-and-replace.

{locations}
Unlock with Pro →

when to use it

Community prompt sourced from the open-source GitHub repo artificialguybr/one-prompt-security-audit (no explicit license). A "REPORT PROMPT" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.

tags

roleplaycommunitygeneral

source

artificialguybr/one-prompt-security-audit · no explicit license