PromptArmor

PromptArmor (YC W24) is an LLM application security platform that detects and blocks enterprise-grade threats - indirect prompt injection, data exfiltration, phishing, and system manipulation - in production AI applications. A real-time detection API analyzes LLM inputs and outputs against a continuously updated set of threat detectors before a completion is acted on, returning a fast verdict (for example containsInjection) so applications can block or allow content.

3 APIs 0 Features

AILLMSecurityPrompt InjectionThreat Detection

APIs

PromptArmor Content Check API

Submits content (such as untrusted text an LLM is about to summarize or act on) to PromptArmor's detection engine and returns a verdict - including a containsInjection flag - in...

PromptArmor Analyze API

Analyzes LLM input (for example an email being summarized) and LLM output (for example the generated summary) through PromptArmor's default and modifiable detectors - data exfil...

PromptArmor Session Monitoring API

When a session_id is supplied on analyze requests, PromptArmor runs session-based anomaly detection, learning normal application behavior and flagging deviations across a sessio...

Resources

Sources

aid: prompt-armor
url: https://raw.githubusercontent.com/api-evangelist/prompt-armor/refs/heads/main/apis.yml
name: PromptArmor
kind: company
description: PromptArmor (YC W24) is an LLM application security platform that detects
  and blocks enterprise-grade threats - indirect prompt injection, data exfiltration,
  phishing, and system manipulation - in production AI applications. A real-time
  detection API analyzes LLM inputs and outputs against a continuously updated set
  of threat detectors before a completion is acted on, returning a fast verdict
  (for example containsInjection) so applications can block or allow content.
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
tags:
- AI
- LLM
- Security
- Prompt Injection
- Threat Detection
created: '2026-06-20'
modified: '2026-06-20'
specificationVersion: '0.19'
apis:
- aid: prompt-armor:prompt-armor-content-check-api
  name: PromptArmor Content Check API
  tags:
  - Security
  - Prompt Injection
  - Threat Detection
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://promptarmor.readme.io/reference/post_v1-check-content
  baseURL: https://api.promptarmor.com
  properties:
  - url: https://promptarmor.readme.io/reference/basics-of-promptarmor-architecture
    type: Documentation
  - url: https://promptarmor.readme.io/reference/post_v1-check-content
    type: APIReference
  - url: openapi/prompt-armor-openapi.yml
    type: OpenAPI
  - url: collections/prompt-armor.postman_collection.json
    type: PostmanCollection
  - url: collections/prompt-armor.opencollection.json
    type: OpenCollection
  description: Submits content (such as untrusted text an LLM is about to summarize
    or act on) to PromptArmor's detection engine and returns a verdict - including
    a containsInjection flag - indicating whether the content matches known threat
    classes. Authenticated with an Api-Key header.
- aid: prompt-armor:prompt-armor-analyze-api
  name: PromptArmor Analyze API
  tags:
  - Security
  - Analyze
  - Detectors
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://promptarmor.readme.io/reference/basics-of-promptarmor-architecture
  baseURL: https://api.promptarmor.com
  properties:
  - url: https://promptarmor.readme.io/reference/basics-of-promptarmor-architecture
    type: Documentation
  - url: openapi/prompt-armor-openapi.yml
    type: OpenAPI
  - url: collections/prompt-armor.postman_collection.json
    type: PostmanCollection
  - url: collections/prompt-armor.opencollection.json
    type: OpenCollection
  description: Analyzes LLM input (for example an email being summarized) and LLM
    output (for example the generated summary) through PromptArmor's default and
    modifiable detectors - data exfiltration, phishing, system manipulation, and
    adversarial instructions - to flag adversarial content in real time before a
    completion is acted on.
- aid: prompt-armor:prompt-armor-session-monitoring-api
  name: PromptArmor Session Monitoring API
  tags:
  - Monitoring
  - Anomaly Detection
  - Sessions
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://promptarmor.readme.io/reference/basics-of-promptarmor-architecture
  baseURL: https://api.promptarmor.com
  properties:
  - url: https://promptarmor.readme.io/reference/basics-of-promptarmor-architecture
    type: Documentation
  - url: openapi/prompt-armor-openapi.yml
    type: OpenAPI
  description: When a session_id is supplied on analyze requests, PromptArmor runs
    session-based anomaly detection, learning normal application behavior and
    flagging deviations across a session that may indicate a security
    vulnerability. Surfaced through the same analyze endpoints rather than as a
    standalone endpoint.
common:
- type: LinkedIn
  url: https://www.linkedin.com/company/promptarmor
- type: Website
  url: https://www.promptarmor.com/
- type: Documentation
  url: https://promptarmor.readme.io/
- type: Plans
  url: plans/prompt-armor-plans-pricing.yml
- type: RateLimits
  url: rate-limits/prompt-armor-rate-limits.yml
- type: FinOps
  url: finops/prompt-armor-finops.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com