ShulkwiSEC/bb-huge / skills/curated/gh-export
gh-export
VerifiedFormats all confirmed pentest findings from findings.json into copy-pasteable GitHub issue markdown blocks, following the AppSec reporting guide template.
GitHub Issue Export
Purpose
Read findings.json from the current pentest session and produce one copy-pasteable GitHub issue markdown block per confirmed finding.
Each block follows the AppSec reporting guide format — concrete impact, reproducible steps, raw PoC — so developers can act immediately without back-and-forth.
Workflow
- Read
findings.jsonfrom the repo root (or the path provided in$ARGUMENTSif given) - For each entry in
findings[].findings(skip diagram entries):- Format it using the template below
- Check
pocs/for any.httpfile whose name contains a keyword from the finding title — if found, read it and paste the content into the PoC block - After formatting the block, call
http(action="request", ...)with methodPATCH, urlhttp://localhost:7777/api/findings/{finding.id}, body{"gh_issue": "<the formatted markdown block>"}, and headers{"Content-Type": "application/json"}— this couples the block to the finding in the dashboard
- Write all formatted blocks to
gh-issues.mdin the repo root, separated by---, with a header line# GitHub Issues — <target> — <date>at the top. Create or overwrite the file. - Print all blocks consecutively with a
---separator between them - After the last block, print a one-line summary:
X issue(s) ready to file — saved to gh-issues.md and copied above.
Output Template
For every finding, output exactly this structure (omit ## Browsers Verified In for non-browser/non-web findings):
**Summary:** <one sentence: what the vulnerability is and which component/endpoint is affected>
**Impact:** <what an attacker can concretely do — name the data exposed, the privilege gained, or the service disrupted. Never write "could lead to" — write "allows an attacker to". One short paragraph.>
**Severity Level:** <Critical | High | Medium | Low>
## Steps To Reproduce:
1. <exact first step — full URL, parameter name, payload>
2. <exact second step>
3. <what to observe in the response that confirms the issue>
## PoC
```
<paste the raw curl command, HTTP request from pocs/*.http, or tool output excerpt that proves exploitability>
```
## Supporting Material/References:
* <CVE ID if applicable, otherwise omit this line>
* Affected target: <target URL or file path from the finding>
* Tool: <tool_used value from the finding>
* <any additional evidence: key excerpt from raw tool output>
## Remediation
<if the finding has a `remediation` field, include this section — otherwise omit it entirely>
**Effort:** <effort level> | **Breaking change:** <Yes/No>
```diff
<paste the diff from remediation.diff, or show before/after from remediation.before and remediation.after>
```
**File:** <remediation.file>:<remediation.line>
**Verification:** <remediation.verification — how to confirm the fix worked>
**References:**
* <each URL from remediation.references>
Rules
- One block per finding — never merge two findings into one issue
- Impact must be concrete — derive it from the finding's
descriptionandevidencefields; never invent hypothetical consequences - Steps to Reproduce must be self-contained — if the finding has a
reproductionfield, use itscommandas the primary reproduction step. Otherwise include full URLs and exact payloads so a developer can reproduce without asking questions - PoC block is mandatory — if a matching
.httpfile exists inpocs/, paste its full content; if the finding hasreproduction.command, include that; otherwise extract the most relevant raw evidence line from theevidencefield - Remediation section — if the finding has a
remediationfield, include the ## Remediation section with the diff, effort level, verification step, and references. If no remediation exists, omit the section entirely - Severity mapping: critical →
Critical, high →High, medium →Medium, low →Low - Output only the markdown blocks and the final summary line — no extra prose, no headers, no explanation around the blocks
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 465k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 465k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 465k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 192k | Updated | Claude CodeCodex | Verified | Install |