Packages / AI And ML Service Credentials
Keys, tokens, and connection secrets for model providers, AI platforms, and machine-learning services.
Detects secrets and credentials surfaced in AI/LLM context: private-key headers (RSA / EC / OpenSSH / generic) and connection-string passwords (password= / pwd=) pasted into prompts, chat exports, or AI-generated output. Reuses the intent of built-in credential SITs, re-scoped to the AI surface.
Detects Azure Bot Framework secret key patterns. This pattern is based on a Microsoft Purview built-in sensitive information type. Users already running Purview may prefer to enable the built-in SIT directly, or use this version as a starting point for customisation.
Detects Azure Bot Service application secret patterns. This pattern is based on a Microsoft Purview built-in sensitive information type. Users already running Purview may prefer to enable the built-in SIT directly, or use this version as a starting point for customisation.
Detects Azure Cognitive Search (AI Search) API key patterns. This pattern is based on a Microsoft Purview built-in sensitive information type. Users already running Purview may prefer to enable the built-in SIT directly, or use this version as a starting point for customisation.
Detects Azure Cognitive Services subscription key patterns. This pattern is based on a Microsoft Purview built-in sensitive information type. Users already running Purview may prefer to enable the built-in SIT directly, or use this version as a starting point for customisation.
Detects Azure Machine Learning web service API key patterns. This pattern is based on a Microsoft Purview built-in sensitive information type. Users already running Purview may prefer to enable the built-in SIT directly, or use this version as a starting point for customisation.
Detects Anthropic (Claude) API keys. Standard keys use the sk-ant-api03- prefix followed by a long base64url body ending in AA; admin keys use sk-ant-admin01-. A leaked key grants billed access to the Anthropic API and any connected data.
Detects Cohere API keys. Cohere issues an opaque 40-character alphanumeric token with no distinctive vendor prefix, so this pattern requires an adjacent Cohere label (cohere / CO_API_KEY / COHERE_API_KEY) to structurally qualify a match.
Detects Groq (GroqCloud) API keys, which use a distinctive gsk_ prefix followed by a long alphanumeric body. A leaked key grants unauthorized, billed access to Groq's hosted inference API and any prompts or data routed through it.
Detects Hugging Face user access tokens (hf_ prefix), used to authenticate to the Hugging Face Hub API. A leaked token grants access to private models, datasets and Spaces, and can incur inference billing.
Detects LangSmith API keys (personal access tokens and service keys), which use a distinctive lsv2_pt_ or lsv2_sk_ prefix followed by a hyphenated hex body. A leaked key grants unauthorized access to LangSmith trace data -- which can include full LLM prompts and completions -- and billed access to the LangSmith/LangChain platform.
Detects Openai Key patterns.
Detects Perplexity API keys, which use a distinctive pplx- prefix followed by a 48-character alphanumeric body. A leaked key grants unauthorized, billed access to Perplexity's search and chat completion API and any prompts or data routed through it.
Detects Pinecone API keys in both current live formats: pcsk_ (the dominant format issued by the Pinecone console, CLI, and SDK key-creation flows) and pckey_ (the Enterprise-plan Admin API variant, format pckey_<public-label>_<unique-key>). A leaked key grants unauthorized access to a Pinecone vector database, including any embeddings or vectorised source data it stores.
Detects Replicate API tokens, which use a distinctive r8_ prefix followed by a fixed-length body of alphanumerics, underscores, and hyphens. A leaked token grants unauthorized, billed access to Replicate's hosted model inference API and any prompts, images, or data routed through it.
Detects xAI (Grok) API keys, which use a distinctive xai- prefix followed by a long alphanumeric body. A leaked key grants unauthorized, billed access to xAI's Grok models and any prompts or data routed through the API.