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 governance-attackgit 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/governance-attack)<a href="https://agentmods.dev/skills/purpleailab/decepticon/governance-attack"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/governance-attack.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00059 | $0.01255 |
| Opus 5 | $0.00030 | $0.00628 |
| Sonnet 5 | $0.00012 | $0.00251 |
| Haiku 4.5 | $0.00006 | $0.00126 |
Grade A, and why
contracts-governance-attack 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 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.
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:
- governance-attack — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DAO Governance Attack
Attack classes
1. Flash-loan-backed vote
DAOs that grant voting power = current token balance (not snapshot of past balance) are vulnerable:
// Attack: borrow governance token, vote, return loan, all in one tx
function attack() external {
// 1. Flash-borrow gov tokens
IFlashLoan(aave).flashLoan(address(this), govToken, 1_000_000e18, "");
}
function executeOperation(...) external {
// 2. Vote on the malicious proposal
governor.castVote(proposalId, 1); // 1 = for
// 3. Repay loan + premium (automatic by flash-loan callback)
}
This is what happened to Beanstalk (April 2022, $182M loss) — attacker flash-borrowed Beanstalk gov tokens, voted to drain the treasury, repaid the loan. Same block.
Defense check: Does getVotes(address, blockNumber) reference a past snapshot? If yes (Compound's GovernorBravo pattern, OZ Governor with ERC20Votes + getPastVotes), flash-loan vote doesn't work.
2. Delegation hijack
ERC20Votes lets users delegate. If a contract holds gov tokens and delegates to itself, controlling that contract = controlling the votes.
// If the target DAO has a contract holding tokens that delegates to itself,
// and that contract is upgradeable/has an admin function:
upgradeableContract.upgradeAndCall(newImpl, abi.encodeWithSelector(redelegate.selector, attacker));
// Now attacker controls those votes.
3. Quorum dilution attack
If quorum = % of total supply (not % of currently-active voters), an attacker can mint or stake extra tokens to push quorum out of reach:
// Some DAOs base quorum on totalSupply()
// Attacker mints a bunch of tokens to themselves (via legit minting if they're holder)
// Quorum requirement now too high for real voters to meet → all proposals fail
4. Proposal spam DoS
GovernorBravo has a proposalThreshold. If low, attacker spams proposals to:
- Burn proposers' gas
- Confuse the UI
- Push real proposals out of the active window
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.
- 3d ago First seen · 123 lines · 59 tokens per session scan A 61e04534496b
contracts-governance-attack is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,451 stars, last pushed 7d ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,255 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.
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.