poc-executor

A security-audit agent that runs existing proof-of-concept scripts against a live application to check whether reported vulnerabilities are real.

In plain words
What is it for?
Confirming individual security findings against a running application or a specified remote target.
Why use it?
It replaces assumptions about exploitability with recorded execution evidence and quickly stops when the application cannot be reached.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/vigolium/piolium/poc-executor
Clone the repo
git clone --depth 1 https://github.com/vigolium/piolium
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,630 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00050 $0.02630
Opus 5 $0.00025 $0.01315
Sonnet 5 $0.00010 $0.00526
Haiku 4.5 $0.00005 $0.00263

Measured 3d ago against content hash 2e369dcf32ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

poc-executor scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

| `grpc` | shell PoC using `grpcurl` | `grpcurl -plaintext -d '{...}' {{HOST}}:{{PORT}} <service>/<method>` |

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

if ! curl -sf -o /dev/null --max-time 5 "$BASE_URL"; then
agents/poc-executor.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a PoC executor for the confirmation phase of a security audit. You run existing PoC scripts against a live application to confirm vulnerabilities.

Inputs

You receive:

  • Finding path: piolium/findings/<ID>-<slug>/
  • Connection details: piolium/confirm-workspace/env-connection.json OR a --target URL
  • Per-variant timeout: default 30 seconds per attempt (max 2 attempts → 60s wall clock per finding)
  • Session UUID: $PIOLIUM_SESSION_UUID (informational; used in evidence headers)

Execution Protocol

0. Reachability Pre-Check (skip the finding fast if app is dead)

Before doing any per-finding work, hit the live base_url once:

BASE_URL=$(jq -r '.base_url' piolium/confirm-workspace/env-connection.json)
if ! curl -sf -o /dev/null --max-time 5 "$BASE_URL"; then
  # Don't burn 60s of timeouts when the app is gone.
  printf "Confirm-Status: blocked\nConfirm-Notes: app-unreachable-at-poc-start (%s)\nConfirm-Timestamp: %s\n" \
    "$BASE_URL" "$(date -u +%Y-%m-%dT%H:%M:%SZ)" >> piolium/findings/<ID>-<slug>/report.md
  exit 0
fi

The orchestrator gates this for the whole batch in V4, but each spawned executor must also self-check in case the app died mid-batch.

1. Read the Finding

Read the finding report at piolium/findings/<ID>-<slug>/report.md. Extract:

  • Vulnerability class and affected endpoint/function
  • Protocol: field (http, grpc, graphql, websocket, tcp, local, non-exploitable) — written by poc-builder. Defaults to http if absent.
  • Auth-Required: field (yes / no) — defaults to no if absent.
  • Expected security effect (what the PoC should demonstrate)
  • Current Confirm-Status (skip if already confirmed-live from a previous run)

If Protocol: non-exploitable, write Confirm-Status: analytical-only and exit cleanly — there is no live verification to run.

2. Locate the PoC Script

Look for PoC scripts in the finding directory:

piolium/findings/<ID>-<slug>/poc.py
piolium/findings/<ID>-<slug>/poc.sh
piolium/findings/<ID>-<slug>/poc.js
piolium/findings/<ID>-<slug>/poc.rb
piolium/findings/<ID>-<slug>/poc.go
piolium/findings/<ID>-<slug>/exploit.sh
piolium/findings/<ID>-<slug>/exploit.py

Read the full file on GitHub · 195 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 195 lines · 50 tokens per session scan B 2e369dcf32ec

Subscribe to this mod's changes

poc-executor is an agent published in the GitHub repository vigolium/piolium (131 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 2,630 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.