Decepticon is an autonomous red-team agent that coordinates AI agents, security tools, sandboxes, and supporting services for authorized cybersecurity assessments. Security researchers and red teams can run it through its Docker stack, cloud service, command-line interface, or Python SDK, with the catalogue entries representing its available skills.
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.
npx skills add PurpleAILAB/Decepticon --skill signature-replaygit clone --depth 1 https://github.com/PurpleAILAB/DecepticonWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/purpleailab/decepticon/signature-replay)<a href="https://agentmods.dev/skills/purpleailab/decepticon/signature-replay"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/signature-replay/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/purpleailab/decepticon/signature-replay"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/signature-replay.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.02363 |
| Opus 5 | $0.00015 | $0.01182 |
| Sonnet 5 | $0.00006 | $0.00473 |
| Haiku 4.5 | $0.00003 | $0.00236 |
Grade A, and why
signature-replay 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- signature-replay — 100% identical, 3 lines differ
How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Signature Replay Playbook
EIP-712 signatures, permits, meta-transactions, and cross-chain bridges
all use ecrecover (or its variants). Each has well-known bugs.
Bug classes
1. Missing nonce → replay
function execute(uint256 amount, bytes calldata sig) external {
bytes32 h = keccak256(abi.encodePacked(msg.sender, amount));
address signer = ecrecover(h, ...);
require(signer == owner);
// ... withdraw amount
}
A valid signature can be replayed forever — anyone who saw it once can re-submit it. Fix: include a per-user / per-message nonce:
mapping(address => uint256) public nonces;
function execute(uint256 amount, uint256 nonce, bytes calldata sig) external {
require(nonce == nonces[msg.sender]);
nonces[msg.sender]++;
bytes32 h = keccak256(abi.encodePacked(msg.sender, amount, nonce));
// ...
}
2. Missing chain ID → cross-chain replay
A signature valid on Ethereum mainnet shouldn't work on Optimism, Base,
Arbitrum, etc. If chainid() not in the signed payload, signatures
replay across chains:
// VULNERABLE
bytes32 h = keccak256(abi.encodePacked(amount, deadline, nonce));
// SAFE — EIP-712 domain separator includes chainid
bytes32 h = _hashTypedDataV4(...); // OZ helper
This is especially bad for bridges — a signed message intended for chain A executes on chain B.
3. Signature malleability (ecrecover variants)
ecrecover accepts two valid s values for any signed message
(s and -s mod n). This means each signature has two valid forms.
If your contract uses the signature itself as a uniqueness key
(e.g., usedSigs[sig] = true), an attacker can find the malleable
version and bypass:
// VULNERABLE — uses sig as uniqueness key
mapping(bytes => bool) public used;
function execute(bytes calldata sig) external {
require(!used[sig]);
used[sig] = true;
address signer = ecrecover(...);
// ...
}
Fix: use the message hash (not the signature) as uniqueness key.
Modern OZ ECDSA library rejects high-s values, but home-rolled
ecrecover does not.
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.
- 9d ago First seen · 266 lines · 31 tokens per session scan A a5cc9e6497a5
signature-replay is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,491 stars, last pushed 13d ago), licensed Apache-2.0. It adds 31 tokens to every session and 2,363 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
langchain-fundamentals
Create LangChain agents with createagent, define tools, and use middleware for human-in-the-loop and error handling.
langsmith-evaluator
INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2) Defining Run Functions - how to capture outputs and trajectories from your agent; (3) Running Evaluations - locally with evaluate() or auto-run via LangSmith. Uses…
devloop
Goal-driven development loop — define objective, write rules with key-results, verify visually, sync to issue tracker.
interactive-dashboard
Interactive web dashboards: stock trackers, sector heatmaps, portfolio monitors — served via preview URL.
onboarding
First-time user onboarding to set up investment profile, watchlists, portfolio, and preferences.
skill0
Root index of x-cmd skill0 sub-skills. Defines the OKR-style agent workflow (goal → rule-verified results → execute), skill discovery, and agent tooling preferences. Style: principle-first, concise, delegate specifics to authoritative external sources.