Aphasia Agentry
Agentic BAS — breach & attack simulation for AI agents and MCP servers. Drive an attacker (curated seed payloads and/or any LLM) against a target, prove impact with per-run canaries, and get a report mapped to the OWASP LLM Top 10 and MITRE ATLAS.
Install
pip install aphasia-agentry # or: uvx aphasia-agentry, pipx install aphasia-agentry
Why
Most agent red-teaming grades a model's output with an LLM judge. Aphasia Agentry asks a harder question — did the attack actually reach impact? — and answers it with evidence:
- Proof, not judgement. A finding is a touched canary record, a used honey token, or a mutating tool call captured by a record-only mirror. Never a model's self-assessment.
- Any LLM, or none. Seed mode runs curated payloads with no LLM at all (reproducible, runs in seconds). Add an adaptive attacker via litellm: OpenAI, Anthropic, Gemini, Groq, OpenRouter, Bedrock, local vLLM/LM Studio, Ollama.
- Full OWASP LLM Top 10. 11 scenarios across LLM01–LLM10, mapped to MITRE ATLAS.
- Safe by construction. The bundled vulnerable fixture is sandbox-inert — real exploit, fake blast radius: no disk, exec, env or network from any attack.
Quickstart
No LLM, no API key — reproducible coverage from the seed-payload library (needs the bundled Docker fixture, from a repo checkout):
docker compose -f fixture/docker-compose.yml up -d
aphasia run --mode seed # then open runs/<id>/report.html
Point it at your own agent instead of the fixture:
aphasia run --target http://host/chat --model gpt-4o-mini # any litellm model
aphasia list shows the scenarios; aphasia payloads the seed library; aphasia --help the rest.
Links
Full documentation, the vulnerable fixture, contributing guide and source: https://github.com/mddanish/Aphasia-Agentry
The bundled fixture is intentionally vulnerable — run it on localhost only, never expose it.
Licensed under Apache-2.0.
Metadata
Release files for aphasia-agentry 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| aphasia_agentry-0.1.1.tar.gz | 211.2 kB | Without provenance | Details for aphasia_agentry-0.1.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| aphasia_agentry-0.1.1-py3-none-any.whl | Python 3 | none | any | Details for aphasia_agentry-0.1.1-py3-none-any.whl |
Total release size: 241.1 kB
Release files / aphasia_agentry-0.1.1.tar.gz
| Download URL | aphasia_agentry-0.1.1.tar.gz |
|---|---|
| Size | 211.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e4d44284bd0efa60a66c925d408933fad24f92307ee6030ba0e402de51c5f6b0
|
|
BLAKE2b-256 checksum How to use checksums |
658ff37e6eb615c1125224bb0702e9560384a0a474edd5a8a1044705ad807b64
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.12.23 {"installer":{"name":"uv","version":"0.12.23","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / aphasia_agentry-0.1.1-py3-none-any.whl
| Download URL | aphasia_agentry-0.1.1-py3-none-any.whl |
|---|---|
| Size | 29.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
395ce66285cfeec6d9bba311ed70ab0f3674f0a5dfb7ff4bb8049113d1833abe
|
|
BLAKE2b-256 checksum How to use checksums |
8fe9b617005372ffb7b44ce026d1603890b1d55036ba89171ce96153b4b1e4b9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.12.23 {"installer":{"name":"uv","version":"0.12.23","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for aphasia-agentry 0.1.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.