RedFang

Web · API · paid plans from $19/mo

Freedom report

Two barsScore 6.4

Free tierA free tier is on its own pricing page
Open codeNo open-source code on record
Runs widely1 of 6 device platforms
DocumentedPlans, terms and facts published

RedFang is ranked #10 of 27 in AI red teaming tools on Freedom251. It runs on API, Web. There is a free plan. Paid plans start at $19/mo.

RedFang plans and pricing

All plans

Free preview Free Grade and top 3 issue categories · no credit card redfang.org · 2 Oct 2026

Full report $19/mo Every finding · reproduction prompt and curl command · fix code · retest · shareable badge redfang.org · 2 Oct 2026

Compared on AI red teaming tools

Free plan: Yes
Attack categories: direct prompt injection; tool misuse; sensitive data leakage; output-as-attack-vector; agent overreach; denial-of-wallet; system-prompt extraction
Target systems: AI agents; GitHub repositories; application URLs; customer-service chatbots; coding agents; LLM workflows
Automation level: continuous
Deployment: cloud
Continuous monitoring: Yes
Report exports: PDF; HTML

Best RedFang alternatives

See all 12

Two bars AgentSeal Free tier No. 1Free6.6 Two bars OpenSecureAI Scanner Free tier No. 2$49/mo6.6 Two bars Promptfoo Free tier No. 3Free6.6 Two bars RedAmon Free tier No. 4Free6.6 One bar Confident AI Free tier No. 5$200/mo6.4 One bar Darkhunt AI Security Free tier No. 6Free6.4

The record

Purpose: RedFang describes itself as an AI red-team scanner for indie builders that scans AI agents, GitHub repositories, and app URLs.
Scan time: RedFang says a scan takes five minutes and returns a grade from A+ to F.
Target verification: Before scanning, RedFang sends a TXT-record or file-upload challenge to confirm ownership of the target.
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.
Repository scanning: RedFang says it scans GitHub repositories for exposed keys, broken authentication, and AI-introduced bugs.
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.
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.
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.
Badge scan cadence: The badge page lists weekly scans for Indie, daily for Team, and continuous scanning for Scale tiers.
Cancellation: The home page says checkout is through Stripe in live mode and customers can cancel anytime.
Maker: The site identifies RedFang as a solo-founder product.
Price from: $19/mo

Where it ranks on Freedom251

Best AI Red Teaming Tools in 2026#10 of 27

Is RedFang yours?

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.

Claim it free Promote RedFang

Sources

redfang.org· checked 2 Oct 2026
redfang.org/how-it-works· checked 2 Oct 2026
redfang.org/badge· checked 2 Oct 2026