poc

A workspace setup and proof-of-concept generator for testing a software vulnerability. A proof of concept is a small script that demonstrates whether a security flaw can be reproduced.

In plain words
What is it for?
Use it to prepare an isolated vulnerability test and generate a standalone proof-of-concept script for the selected flaw.
Why use it?
It removes the manual work of finding the vulnerable file, preparing folders, and installing the needed packages before testing. It also provides the exact working paths needed to create the test script.

Skill for Claude CodeCodex

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 skills/gemini-cli-extensions/security/poc
Any agent
npx skills add gemini-cli-extensions/security --skill poc
Clone the repo
git clone --depth 1 https://github.com/gemini-cli-extensions/security

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 423 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00025 $0.00423
Opus 5 $0.00013 $0.00211
Sonnet 5 $0.00005 $0.00085
Haiku 4.5 $0.00003 $0.00042

Measured 2d ago against content hash c193f694944a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

poc scanned grade A with 0 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 2d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/poc/SKILL.md · 27 lines

What it actually says

You are a security expert. Your task is to generate a Proof-of-Concept (PoC) for a vulnerability. You MUST call the poc_context tool BEFORE attempting to write any PoC code. The poc_context tool will execute the setup and return the exact context and directory paths you need to actually generate the PoC script. If multiple vulnerabilities are present, use the ask_user tool to ask which one to test.

Your Steps:

  1. Call poc_context Tool:

    • Extract the problemStatement, vulnerabilityType, and exact sourceCodeLocation from the user context. If the problemStatement does not contain the exact file path, you MUST use your search tools to find the vulnerable file in the codebase BEFORE calling the tool.
    • Call the poc_context tool with these arguments.
    • The tool will return JSON containing coordinates: language, pocDir, pocFileName, and extraInstructions. Keep these coordinates for the following steps.
  2. Use Dependency Manager Guidelines:

    • Use the dependency-manager skill to install dependencies for the PoC.
  3. Generate PoC:

    • The PoC directory pocDir has been created for your scratchwork.
    • Generate your standalone script named exactly as pocFileName under the returned pocDir.
    • Pay attention to any extraInstructions returned by poc_context.
  4. Run PoC:

    • Use the run_poc tool with the absolute file path to the generated PoC file to execute the code.
    • Analyze the output to verify if the vulnerability is reproducible.
    • If reproducible, use the ask_user tool to ask if the user wants to fix it.
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. 2d ago First seen · 27 lines · 25 tokens per session scan A c193f694944a

Subscribe to this mod's changes

poc is a skill published in the GitHub repository gemini-cli-extensions/security (791 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 423 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.