Skip to content
SPECIFICTION
Get listed

PromptRedTeam

promptredteam.com

Free plan WebAPISelf-hosted
Visit promptredteam.com
Spec score 7.8 #11 of 27 in AI Red Teaming Tools

What it is

PromptRedTeam is an open-source tool that scans user input before it reaches a large language model. It detects direct injection, role manipulation, zero-width injection, delimiter injection, and encoded payloads. Direct-injection checks examine override keywords, conflicting instructions, and prompt structure. Role checks cover known jailbreak patterns, role-play scenarios, and bypass attempts. The tool detects hidden zero-width characters, normalizes Unicode, analyzes Base64 and other encodings, and can decode suspicious text before scanning again. Delimiter checks look for context-breaking markers, Markdown abuse, and structural manipulation. Applications can call the hosted API with a POST request to https://api.promptredteam.com/test, or run PromptRedTeam through self-hosted deployment. The live tester accepts up to 1,000 characters and allows 10 requests per minute; self-hosting provides unlimited usage. Python, JavaScript, and cURL examples are provided. The suggested workflow is to scan incoming text, then block detected threats or log them for review. PromptRedTeam is available through web, API, and self-hosted platforms, with automated detection and hybrid deployment. It is released under the MIT License.

Spec sheet

Purpose
PromptRedTeam scans user inputs for prompt injection before they reach an LLM.Read 9 Oct 2026 · promptredteam.com
License
The homepage describes PromptRedTeam as open source under the MIT License.Read 8 Oct 2026 · promptredteam.com
Attack coverage
It detects direct injection, role manipulation, zero-width injection, delimiter injection, and encoded payloads.Read 8 Oct 2026 · promptredteam.com
Company details
The opened maker page does not state the maker's name, headquarters, or founding year.Read 9 Oct 2026 · promptredteam.com
Delimiter detection
The site says it detects context-breaking delimiters, markdown abuse, and structural manipulation.Read 8 Oct 2026 · promptredteam.com
Detection categories
It detects direct injection, role manipulation, zero-width injection, delimiter injection, and encoded payloads.Read 9 Oct 2026 · promptredteam.com
Direct injection detection
The site says direct injection detection uses pattern matching for override keywords, instruction conflicts, and prompt structure analysis.Read 8 Oct 2026 · promptredteam.com
Hidden and encoded text
The site describes zero-width character detection, Unicode normalization, Base64 and encoding analysis, and automatic decoding and rescanning.Read 8 Oct 2026 · promptredteam.com
Hosted API
The site demonstrates sending text to https://api.promptredteam.com/test using a POST request with JSON.Read 9 Oct 2026 · promptredteam.com
Integration examples
The site provides implementation examples for Python, JavaScript, and cURL.Read 9 Oct 2026 · promptredteam.com
Live testing limit
The live demo allows 10 requests per minute and accepts up to 1,000 characters in its input field.Read 9 Oct 2026 · promptredteam.com
Open source license
The site describes the project as open source under the MIT License.Read 9 Oct 2026 · promptredteam.com
Rate limit
The live tester allows 10 requests per minute and says deploying your own provides unlimited usage.Read 8 Oct 2026 · promptredteam.com
Role manipulation detection
The site says role manipulation detection recognizes known jailbreak patterns, role-play scenarios, and bypass attempts.Read 8 Oct 2026 · promptredteam.com
Self-hosting
The site says users can self-host for unlimited usage.Read 9 Oct 2026 · promptredteam.com
Suggested use
The homepage suggests scanning inputs before they reach an LLM, then blocking threats or logging them for review.Read 8 Oct 2026 · promptredteam.com
Workflow
The site says applications can scan inputs before they reach an LLM and block threats or log them for review.Read 9 Oct 2026 · promptredteam.com

Plans and prices

Open source Free Hosted demo: 10 requests/min · Self-hosted: unlimited usage Read 9 Oct 2026 · promptredteam.com

Every PromptRedTeam plan and price →

Strong points and limits

Strong points

  • Detects five listed attack categories
  • Unicode and encoded-payload analysis
  • Hosted API available
  • Self-hosting offers unlimited usage
  • Python, JavaScript, and cURL examples

Limits

  • Hosted tester limited to 10 requests per minute
  • Live input capped at 1,000 characters
  • Threat handling requires blocking or logging workflow

Who it suits

It suits teams adding automated prompt-threat checks before sending user input to LLMs. Self-hosting fits deployments needing unlimited usage.

Verdict

PromptRedTeam focuses on inspecting prompts for injection, manipulation, hidden characters, delimiters, and encoded content. You can use its hosted API or self-host it, with different usage limits.

Where Specifiction places it

Alternatives to PromptRedTeamAll alternatives →