Skip to content
View Pyhroff's full-sized avatar

Highlights

  • Pro

Organizations

@zka19-team

Block or report Pyhroff

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Pyhroff/README.md

Praising Harris Ratnam

AI Security Engineer · AI Engineer, with a cybersecurity backbone

Python-native · B.Tech CSE (Cybersecurity), IIIT Kottayam, batch of 2028

Portfolio LinkedIn Email PyPI


What I do

I build and measure security tooling for AI agents, and I build the agent and ML systems themselves. The tooling is written in Python. Across my public repositories, the code that is not Python is limited to front ends (the Next.js dashboard in soc-parallax and a few single-file HTML demos) and one Rust file used as a test fixture in pqc-scanner.

My security background (detection engineering, application security, threat modelling) shapes how I build AI systems: treat model output and tool metadata as untrusted input, enforce controls in code rather than in the prompt, and publish what a detector misses next to what it catches.

Open to: internships May-Jul 2027, full-time roles from 2028 (AI security, AI engineering, application security; India or remote).


Flagship projects

Project What it is Measured result
aisec-suite (PyPI 0.11.0) CI security gate for what AI agents trust: MCP tool metadata, agent memory files, RAG documents. SARIF output, baselines, reachability analysis, an MCP runtime guard and an LLM red-team CLI. Structural poisoning detector: 53.7% recall on my held-out attacks, 14.0% on other researchers' attacks (MCPTox, MCP-Poison-Bench), 0.05% false positives on 3,974 real tool descriptions (2 flagged). It misses roughly half of unseen attacks, and the README says so.
mcp-scan-study Hand-labelled study of 135 public MCP-server repos, with the scanner patches that came out of it. No real tool poisoning found in the wild. mcpaudit precision went from 37.5% to 64.3% on a held-out sample, and from 40% to 72.7% on a blind-labelled fresh corpus.
mcpaudit · memsentry · ragsentry The three scanners behind aisec-suite: MCP tool surfaces, agent memory/context files, RAG source documents. On attacks written by others, memsentry and ragsentry catch the stock "ignore previous instructions" phrase and 0-3% of attacks without it.
soc-parallax Detection platform: per-entity behavioural baselines, an attributable risk score, MITRE ATT&CK mapping from a versioned rulebook, incident correlation in Neo4j, grounded narratives. FastAPI, PostgreSQL, Next.js. On 278 real EVTX attack samples, 29.5% reach medium severity or higher (27.3% on a held-out half). Nothing reaches high on held-out benign data. An earlier inflated 53% figure was found in an audit and replaced.
osiris Model-agnostic assistant runtime: 8 LLM providers behind one failover router, tool-scoped agents, embedding memory. I use it daily. Traced a local-model slowdown to Ollama's thinking mode and fixed it with a native adapter (about 100 s to 10 s per call, measured live).

More in the portfolio: PhantomGrid (behavioural biometrics for banking fraud, team hackathon project), promptstrike (multi-turn LLM red-teaming), loopcheck (agent-loop waste auditor), darkdecoder (ATT&CK + ATLAS threat-intel analysis).


Upstream open source

7 pull requests merged and 13 open at the last check (13 Nov 2026). Live status is on each PR; the full table is on the portfolio.

Merged What it fixed
tobymao/sqlglot #8780 Parser._replace_lambda shared one DataType node between several casts.
PrefectHQ/fastmcp #6063 Host callbacks were not counted against the Monty sandbox time limit; added a wall-clock timeout and a call budget.
BerriAI/litellm #47091 A string stop value is now wrapped for Cohere stop_sequences.
sqlfluff #8899, #8901, #8902, #9059 Dialect grammar fixes for StarRocks, Doris and MySQL.

Open work includes authorization fixes in LiteLLM (#47105), MCP pagination in CrewAI (#8240), and fixes in PennyLane, Qualtran, Graphene and Presidio.


Stack

  • Language: Python (asyncio, FastAPI, Pydantic, pytest, AST analysis, scikit-learn)
  • AI engineering: LLM tool-calling and agent loops, provider routing and failover, embeddings and retrieval, evaluation harnesses, local models with Ollama
  • AI security: MCP security, prompt injection and tool poisoning, RAG and memory poisoning, LLM red-teaming (PAIR, TAP, Crescendo), OWASP Top 10 for LLMs, runtime guards, SARIF
  • Security foundations: MITRE ATT&CK and ATLAS, Sigma, threat modelling (STRIDE), detection engineering, Z3 model checking
  • Data and infra: PostgreSQL, Neo4j, SQLite, Docker, GitHub Actions
  • Practice: TryHackMe top 2% globally

Writing


How I work

Every number links back to a script, a labelled dataset or a study document. Where a result is weak, the README says so: single labeller, synthetic data, held-out sets evaluated more than once. AI coding assistants were used on some projects and are disclosed in those READMEs.

Pinned Loading

  1. aisec-suite aisec-suite Public

    Run static security scanners over AI-agent projects: MCP servers, agent memory files and RAG documents. SARIF output, baselines and reachability analysis.

    Python

  2. mcp-scan-study mcp-scan-study Public

    Empirical study of 135 public MCP-server repos: hand-labelled scanner findings with confidence intervals, and a measured false-positive reduction.

    Python

  3. soc-parallax soc-parallax Public

    SOC detection platform: attributable risk scores, MITRE ATT&CK rulebook, incident correlation in Neo4j, evidence-checked narratives. FastAPI, PostgreSQL, Next.js.

    Python 1

  4. ModelHawk ModelHawk Public

    Static scanner that detects code-execution backdoors in PyTorch/pickle ML model files (pickle-deserialization RCE), with an offensive demo generator. Python, stdlib-only.

    Python 1

  5. promptstrike promptstrike Public

    Automated adversarial red-teaming CLI for LLMs — PAIR/TAP/Crescendo jailbreak algorithms, live dashboard, multi-model sweep comparison, CI/CD safety gate

    Python 1