- Home
- AI Red Teaming Tools
- Advent Prompt Pwn
On the recordRead 5 Oct 202623 facts
Advent Prompt Pwn
On the record
- Assessment workflow
- It connects attack case generation to explicit scope, bounded execution, deterministic oracles, resumable checkpoints, reporting, and regression comparison.adventcybersecurity.com · read 5 Oct 2026
- Attack coverage
- Strategies cover direct, instruction override, delimiter, encoding, role confusion, indirect injection, and multi-turn attacks, with mutation and RAG poisoning listed as 1.1 preview features.adventcybersecurity.com · read 5 Oct 2026
- Attack features
- Documented strategies include direct, instruction override, delimiter, encoding, role confusion, indirect injection, and multi-turn testing.adventcybersecurity.com · read 5 Oct 2026
- Availability
- Installation requires Python 3.10 or newer and is documented for PowerShell, macOS, or Linux shells.adventcybersecurity.com · read 5 Oct 2026
- Evidence and reports
- It produces JSON, JSONL, Markdown, HTML, JUnit, and SARIF reports, plus evidence bundles with checksums and per-attempt SHA-256 hashes.adventcybersecurity.com · read 5 Oct 2026
- Evidence handling
- Evidence bundles include a checksum manifest and per-attempt SHA-256 hashes; the documentation says to treat model output as confidential assessment material.adventcybersecurity.com · read 5 Oct 2026
- Integrations
- Targets include custom HTTP JSON APIs, OpenAI-compatible APIs, Ollama, Python callbacks, and preview adapters for OpenAI, Azure OpenAI, Anthropic, and Gemini.adventcybersecurity.com · read 5 Oct 2026
- Known limitations
- Oracle matches require practitioner review, redaction may miss sensitive values, and the static tool sandbox is not a production agent runtime.adventcybersecurity.com · read 5 Oct 2026
- Known limits
- Oracle matches require practitioner review, redaction may miss sensitive values, and the static tool sandbox is not a production agent runtime.adventcybersecurity.com · read 5 Oct 2026
- License
- The project’s GitHub page identifies the source as Apache License 2.0.github.com · read 5 Oct 2026
- Maker
- The product is maintained by Advent Cybersecurity LLC; the maker page identifies Jashid Sany as its founder.github.com · read 5 Oct 2026
- Maturity
- Version 1.0.0 is the stable public release; the 1.1 source line remains beta pending independent practitioner review and field assessment.adventcybersecurity.com · read 5 Oct 2026
- Outcome checks
- Built-in oracles can check strings, canary leaks, regular expressions, JSON keys and paths, and tool calls, including combined conditions.adventcybersecurity.com · read 5 Oct 2026
- Purpose
- Advent Prompt Pwn is a typed Python toolkit for authorized adversarial testing of language models and AI applications.adventcybersecurity.com · read 5 Oct 2026
- Python API
- The toolkit provides a Python API for configuring cases, targets, scope, runs, and reports.adventcybersecurity.com · read 5 Oct 2026
- Reports
- Supported report formats are JSON, JSONL, Markdown, HTML, JUnit, and SARIF.adventcybersecurity.com · read 5 Oct 2026
- Scope controls
- Remote assessments support exact host and port allowlists, authorization windows, DNS controls, and request, rate, concurrency, retry, timeout, and evidence limits.adventcybersecurity.com · read 5 Oct 2026
- Security controls
- Remote assessments can be bounded by exact host and port grants, DNS checks, authorization windows, request limits, and workload ceilings.adventcybersecurity.com · read 5 Oct 2026
