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 bridge-exploitgit 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/bridge-exploit)<a href="https://agentmods.dev/skills/purpleailab/decepticon/bridge-exploit"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/bridge-exploit/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/bridge-exploit"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/bridge-exploit.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 | $0.00064 | $0.01350 |
| Opus 5 | $0.00032 | $0.00675 |
| Sonnet 5 | $0.00013 | $0.00270 |
| Haiku 4.5 | $0.00006 | $0.00135 |
Grade A, and why
contracts-bridge-exploit 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:
- bridge-exploit — 98% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-Chain Bridge Attack
Bridges hold large pooled assets and execute messages from a separate trust layer. Architecturally fragile.
Bridge taxonomy
| Type | Trust model | Past exploits |
|---|---|---|
| Lock-and-mint | Trusted validators sign mint events | Wormhole ($325M), Ronin ($600M), Harmony ($100M) |
| Burn-and-redeem | Same | Multichain/Anyswap ($126M) |
| Optimistic | Fraud proof window | Nomad ($190M) |
| Light-client / zk | Cryptographic | (Fewer hacks, but newer) |
| Liquidity-network (Hop, Connext) | Routers + relayers | Smaller individual exploits |
Attack classes
1. Validator-signature bypass (Wormhole, Feb 2022, $325M)
The Solana-side verify_signature function trusted the caller to provide a "verified" sigset account. Attacker passed a sysvar that wasn't a real sigset → unauthorized mint of 120k wETH.
Lesson: any verify function whose input is a struct fetched by address is bypassable if address-trust is missing.
2. Validator key compromise (Ronin, March 2022, $600M)
9-of-9 validators, 5 of which were operated by one entity. Sky Mavis got phished → attacker controlled 5 keys → arbitrary mint.
Lesson: validator decentralization isn't math, it's operational. Count distinct legal entities and key-storage methods, not just keys.
3. Merkle-proof forgery (Nomad, August 2022, $190M)
After an upgrade, the zero-hash was set as a "valid root" — any proof against root = 0 passed. The first attacker withdrew real funds; then thousands of others copy-pasted the same tx with their own address. ~$190M total.
Lesson: check initialize / upgrade scripts for accidental defaults — bytes32(0), address(0), 1 (often the most-tested value) becoming the trusted value.
4. Replay across chains (Multichain class)
Bridge tx signed for chain A is replayed on chain B because chainId wasn't bound into the signed message:
function claim(bytes32 nonce, uint256 amount, bytes calldata sig) external {
bytes32 hash = keccak256(abi.encode(nonce, msg.sender, amount)); // ⚠ no chainId
require(ecrecover(hash, ...) == validator);
token.transfer(msg.sender, amount);
}
// On chain A: legit claim
// On chain B (same validator, same token): replay the same sig
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 · 115 lines · 64 tokens per session scan A 8e9ba92bace1
contracts-bridge-exploit is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,491 stars, last pushed 13d ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,350 once invoked, about $0.0003 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.
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.
idea-generation
Stock screening and idea generation: quantitative screens, thematic analysis, shortlist.