vigolium/piolium

A Pi-native extension for thorough, agentic security audits

This repository also configures its own agents. See what piolium tells them →

134Stars on the repository
56Mods indexed here, across every type
1mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

poc-executor

25

vigolium/piolium

Agent Claude Code

Confirmation phase V4 PoC execution agent that runs existing PoC scripts from piolium/findings/ against the live application environment or a remote target, adapts connection details, captures execution evidence, and updates finding confirmation status.

not rated 134 +3 1mo ago B 50 tokens original MIT

probe-strategist

26

vigolium/piolium

Agent Claude Code

Probe Strategist — coordinator for a Deep Probe team. Reads the Knowledge Base, maps the attack surface and Layer Trust Chain, authors the Code Anatomy inline, runs backward-reasoner + contradiction-reasoner in parallel, performs Cross-Pollination, dispatches evidence-harvester (which also owns causal challenge), and…

not rated 134 +3 1mo ago A 91 tokens original MIT

report-assembler

27

vigolium/piolium

Agent Claude Code

Phase 13 final report compilation agent that collects all confirmed findings from piolium/findings/ directories, reads adversarial consensus documents and debate transcripts, produces the consolidated pentest-style piolium/final-audit-report.md, and runs all consistency checks.

not rated 134 +3 1mo ago A 55 tokens original MIT

spec-gap-analyst

28

vigolium/piolium

Agent Claude Code

Phase 9 RFC, specification, and framework-contract compliance analysis agent that identifies gaps between documented or implicit platform requirements and codebase implementation, focusing on parsing, normalization, canonicalization, state-machine compliance, middleware semantics, and hidden control channels.

not rated 134 +3 1mo ago A 53 tokens original MIT

vigolium/piolium

Agent Claude Code

Phase 7 state-machine, concurrency, and business-logic audit agent that identifies state-holding entities (status/lifecycle columns, financial balances, idempotency stores) and concurrency primitives, then systematically hunts for TOCTOU, transaction-isolation bugs, state-ordering violations, idempotency failures…

not rated 134 +3 1mo ago A 99 tokens original MIT

static-analyzer

30

vigolium/piolium

Agent Claude Code

Phase 4 SAST orchestration agent that runs Sub-step 4.1 structural extraction, CodeQL security suites, Semgrep with Pro engine, generates custom rules from Phase 3 DFD/CFD blind spots and library attack patterns, manages SAST concurrency, classifies each candidate finding for security relevance (inline enrichment)…

not rated 134 +3 1mo ago B 82 tokens original MIT

test-mapper

31

vigolium/piolium

Agent Claude Code

Confirmation phase V5 test-based verification agent that maps unconfirmed findings to existing test files, generates minimal reproducer tests targeting each vulnerability, executes them in isolation within piolium/findings/ /, and updates confirmation status.

not rated 134 +3 1mo ago C 49 tokens original MIT

variant-hunter

32

vigolium/piolium

Agent Claude Code

Phase 12 per-finding variant analysis agent that takes a confirmed vulnerability and searches for structural variants using the attack pattern registry's detection signatures, CodeQL on-demand queries, DFD/CFD slice analysis including Phase 10 Addendum discoveries, and chamber variant candidates.

not rated 134 +3 1mo ago A 57 tokens original MIT

variant-scout

33

vigolium/piolium

Agent Claude Code

Phase 10 Review Chamber concurrent variant hunter that monitors debate transcripts for confirmed vulnerability patterns and immediately searches for structural variants in sibling components, alternate transports, and adjacent enforcement paths, front-loading Phase 12 variant analysis while chamber context is hot.

not rated 134 +3 1mo ago A 50 tokens original MIT

wave-verifier

34

vigolium/piolium

Agent Claude Code

Cross-agent reinvest verifier. Independently re-verifies a single CRITICAL or HIGH finding under a different agent platform / model than the one that originally produced it. Reads the finding's prior wave verdicts (if any), restates the claim from the report alone, traces from source independently, and emits CONFIRMED…

not rated 134 +3 1mo ago A 97 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: