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 access-controlgit 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/access-control)<a href="https://agentmods.dev/skills/purpleailab/decepticon/access-control"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/access-control/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/access-control"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/access-control.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 | $0.00026 | $0.01720 |
| Opus 5 | $0.00013 | $0.00860 |
| Sonnet 5 | $0.00005 | $0.00344 |
| Haiku 4.5 | $0.00003 | $0.00172 |
Grade A, and why
access-control 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 6d 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:
- access-control — 94% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Access Control Playbook
Access control bugs are the most boring class — and the most common in production audits. They're cheap to find with grep + LSP. They drain millions when missed (LeetSwap, Audius, Saddle, Akropolis).
Audit steps
1. Find every state-changing function
# Functions that are NOT view/pure and NOT internal/private
grep -rE 'function [a-zA-Z_]+\(.*\)(public|external)' src/ | grep -v 'view\|pure'
# Or via slither
slither . --print function-summary
2. For each external/public state-changer, ask
- Does it modify storage that affects user funds, ownership, or configuration?
- Is there a modifier (
onlyOwner,onlyRole,onlyDAO, custom auth)? - If yes, what's the modifier checking?
- If no, should there be one?
3. Audit each modifier
Common modifier patterns + bugs:
| Pattern | Bug |
|---|---|
require(msg.sender == owner) |
owner settable by anyone? setOwner unprotected? |
require(msg.sender == tx.origin) |
Wrong — tx.origin breaks meta-transactions, AND it's phishable |
_msgSender() in OZ ERC2771Context |
Forwarder trusted but anyone can forward — does the contract validate the forwarder? |
onlyRole(MINTER) |
Who can grant MINTER? Is the admin a multisig or single key? |
require(initialized == false) |
Initializer can be called twice if initialized writeable elsewhere |
require(block.timestamp > deployTime + 24 hours) |
Time-based is often a fake delay — check if deployTime is settable |
require(approvedSigners[msg.sender]) |
Approval list managed by single key? |
4. Specific anti-patterns to grep
# Functions accidentally external (default in Solidity <0.5)
grep -rn 'function [a-zA-Z_]*[^ ]* *{' src/ | grep -v 'internal\|private\|public\|external'
# msg.sender == tx.origin (phishable)
grep -rn 'tx.origin' src/
# Reentrancy in access-control checks
grep -rn 'onlyOwner.*nonReentrant' src/ # both? often wrong order
# `delegatecall` without auth gate
grep -rn 'delegatecall' src/
# `selfdestruct` available
grep -rn 'selfdestruct\|suicide(' src/
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.
- 6d ago First seen · 204 lines · 26 tokens per session scan A 007c0470c7c5
access-control is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,471 stars, last pushed 10d ago), licensed Apache-2.0. It adds 26 tokens to every session and 1,720 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 2026-09-03.
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.