Skip to content
SPECIFICTION
Get listed

RedFang

redfang.org

From $19/mo Free plan WebAPI
Visit redfang.org
Spec score 7.5 #18 of 27 in AI Red Teaming Tools

What it is

RedFang is a cloud AI red-team scanner aimed at indie builders. It scans AI agents, GitHub repositories and application URLs, including listed customer-service chatbot targets. Before scanning, it requires a TXT-record or file-upload challenge to verify target ownership. RedFang says scans take five minutes and return grades from A+ to F. Seven v1 categories cover direct prompt injection, tool misuse, sensitive data leakage, output-as-attack-vector, agent overreach, denial-of-wallet and system-prompt extraction. Repository scans look for exposed keys, broken authentication and AI-introduced bugs. The stated methodology follows the OWASP LLM Top 10 threat model and tests 12 known direct prompt-injection patterns per scan. Reports can include plain-language findings, the successful prompt, a curl reproduction command, fix code and a retest. PDF and HTML exports are listed. Free preview costs nothing; Full report costs $19 a month. A shareable badge shows the latest grade, with weekly, daily or continuous scan cadence by tier.

Spec sheet

Purpose
RedFang describes itself as an AI red-team scanner for indie builders that scans AI agents, GitHub repositories, and app URLs.Read 2 Oct 2026 · redfang.org
Maker
The site identifies RedFang as a solo-founder product.Read 2 Oct 2026 · redfang.org
Badge scan cadence
The badge page lists weekly scans for Indie, daily for Team, and continuous scanning for Scale tiers.Read 2 Oct 2026 · redfang.org
Cancellation
The home page says checkout is through Stripe in live mode and customers can cancel anytime.Read 2 Oct 2026 · redfang.org
Certification badge
Customers can embed a badge that updates with the latest scan grade; RedFang says the badge flips within 24 hours if the grade drops.Read 2 Oct 2026 · redfang.org
Methodology
RedFang says its methodology is built on the OWASP LLM Top 10 threat model and tests 12 known direct prompt-injection patterns on every scan.Read 2 Oct 2026 · redfang.org
Report contents
Reports include findings in plain English, the prompt that worked, a curl reproduction command, fix code, and a retest after the issue is fixed.Read 2 Oct 2026 · redfang.org
Repository scanning
RedFang says it scans GitHub repositories for exposed keys, broken authentication, and AI-introduced bugs.Read 2 Oct 2026 · redfang.org
Scan time
RedFang says a scan takes five minutes and returns a grade from A+ to F.Read 2 Oct 2026 · redfang.org
Target verification
Before scanning, RedFang sends a TXT-record or file-upload challenge to confirm ownership of the target.Read 2 Oct 2026 · redfang.org
Threat coverage
Its seven v1 threat categories include direct prompt injection, tool misuse, sensitive data leakage, output-as-attack-vector, agent overreach, denial-of-wallet, and system-prompt extraction.Read 2 Oct 2026 · redfang.org

Plans and prices

Free preview Free Grade and top 3 issue categories · no credit card Read 2 Oct 2026 · redfang.org
Full report $19 a month Every finding · reproduction prompt and curl command · fix code · retest · shareable badge Read 2 Oct 2026 · redfang.org

Every RedFang plan and price →

Strong points and limits

Strong points

  • Five-minute scans with letter grades
  • Seven listed threat categories
  • Repository and application scanning
  • Reproduction commands and fix code
  • PDF and HTML report exports

Limits

  • Full report costs $19 a month
  • Ownership challenge required before scanning
  • Free preview shows only top three categories
  • Badge cadence varies by tier

Who it suits

It suits indie builders wanting cloud scans of AI agents, repositories or app URLs. Teams needing recurring badge updates, continuous monitoring or exported reports may use the paid offering.

Verdict

RedFang combines target verification, defined AI threat coverage and reports that include reproduction and remediation details. The free preview is limited, while the paid plan adds complete findings, retesting and a shareable badge.

Where Specifiction places it

Alternatives to RedFangAll alternatives →