Runtime security for AI agents — detects jailbreak, prompt injection, and tool misuse from inside the agent.

Navigation

Verified details

These details have been verified by PyPI
Maintainers
Avatar for daridor_sprk3 from gravatar.com daridor_sprk3

Unverified details

These details have not been verified by PyPI
Project links
Meta
  • License Expression: MIT
    SPDX License Expression
  • Author: SPR{K}3 Security Research
  • Tags agents , ai , anthropic , langchain , openai , prompt-injection , security
  • Requires: Python >=3.9
  • Provides-Extra: all , anthropic , langchain , openai
Report project as malware

Project description

SPR{K}3 Defend Agents

Runtime security for AI agents — detects jailbreak, prompt injection, and tool misuse from inside the agent, not at the gateway.

Install

pip install sprk3-defend-agents

Quick Start

from sprk3.defend import monitor
monitor(api_key="sk-...")

That's it. Auto-instruments Anthropic, OpenAI, and LangChain clients.

What it detects

  • Indirect prompt injection — hidden instructions in web pages, emails, docs, tool outputs
  • Tool misuse — legitimate tools used on attacker's behalf
  • Agent tamper — heartbeat detects monitoring disabled or bypassed
  • Behavioral anomaly — tool velocity spikes, entropy shifts, new tool usage

Privacy

All detection runs client-side. Server sees metadata only. Evidence stays on your machine.

Links

Project details

Verified details

These details have been verified by PyPI
Maintainers
Avatar for daridor_sprk3 from gravatar.com daridor_sprk3

Unverified details

These details have not been verified by PyPI
Project links
Meta
  • License Expression: MIT
    SPDX License Expression
  • Author: SPR{K}3 Security Research
  • Tags agents , ai , anthropic , langchain , openai , prompt-injection , security
  • Requires: Python >=3.9
  • Provides-Extra: all , anthropic , langchain , openai

Release history Release notifications | RSS feed

This version

0.1.0

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

sprk3_defend_agents-0.1.0.tar.gz (7.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

sprk3_defend_agents-0.1.0-py3-none-any.whl (11.0 kB view details)

Uploaded Python 3

File details

Details for the file sprk3_defend_agents-0.1.0.tar.gz.

File metadata

  • Download URL: sprk3_defend_agents-0.1.0.tar.gz
  • Upload date:
  • Size: 7.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.9.6

File hashes

Hashes for sprk3_defend_agents-0.1.0.tar.gz
Algorithm Hash digest
SHA256 bb6dbf9e58f9bc64fff9d7ca6c232fe549073b20b4656b80ce507657e52126c9
MD5 404b0ea24690b37251be421a9903433a
BLAKE2b-256 184d981b0441eadcf23a69ea05c27caa07732975f13cd5577cdf9425bd0af8d1

See more details on using hashes here.

File details

Details for the file sprk3_defend_agents-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for sprk3_defend_agents-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 86932b40129371fe6ab65d0c739baee68606eb4a42c8fd50d2819652601187f8
MD5 471e39785d5efd3999bf7097da621350
BLAKE2b-256 d50ff95f5c6341bf918b2520717fa9f6811a03b117ad5b3f5fc4b68c90c2b031

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page