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 upgradeable-proxygit 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/upgradeable-proxy)<a href="https://agentmods.dev/skills/purpleailab/decepticon/upgradeable-proxy"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/upgradeable-proxy/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/upgradeable-proxy"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/upgradeable-proxy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 126 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
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 | $0.00028 | $0.01960 |
| Opus 5 | $0.00014 | $0.00980 |
| Sonnet 5 | $0.00006 | $0.00392 |
| Haiku 4.5 | $0.00003 | $0.00196 |
Grade B, and why
upgradeable-proxy scanned grade B with 1 finding 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
attackers can pass their own contract → execute arbitrary code in Copies of this mod
1 near-identical copy found in the catalogue:
- upgradeable-proxy — 97% identical, 3 lines differ
How it starts
The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upgradeable Proxy Playbook
Proxies separate storage (proxy) from logic (implementation). The
proxy delegatecalls into the implementation, executing logic in the
proxy's storage context. Three common patterns:
- Transparent Proxy (OZ TransparentUpgradeableProxy)
- UUPS (OZ UUPSUpgradeable, OZ 4.1+)
- Diamond / EIP-2535 (multi-facet, much more complex)
Each has distinct bug classes.
Audit checklist
1. Uninitialized implementation
Implementations should be initialized at deployment to prevent third-party initialization:
// Vulnerable — anyone can call initialize() on the implementation
// directly (not via proxy) and become its owner
contract VulnImpl {
function initialize(address owner_) external {
owner = owner_;
}
}
// Safe — disable initializers on impl deployment
contract SafeImpl is Initializable {
constructor() { _disableInitializers(); }
function initialize(address owner_) external initializer {
owner = owner_;
}
}
Attack: attacker calls initialize on the impl contract → becomes
"owner" of the impl. While this doesn't immediately drain the proxy,
it CAN matter if _authorizeUpgrade reads impl-side state, or if
selfdestruct is exposed and impl auth is on owner. Past incident:
Parity multisig 2017 — $280M frozen.
# Find unprotected impl
grep -rn 'initialize\|_disableInitializers' src/
2. Storage slot collisions
Proxy and impl share storage. New impl versions must lay storage identical to old:
// V1
contract LogicV1 {
address public owner; // slot 0
uint256 public total; // slot 1
}
// V2 — BUG: inserted new var at top
contract LogicV2 {
uint256 public newVar; // slot 0 — overwrites owner!
address public owner; // slot 1
uint256 public total; // slot 2
}
After upgrade, owner is read from where total was; arbitrary value.
Check:
- New vars only appended at the end
- Inheritance order unchanged
- OZ
__gapreserved slots used in upgradeable libs
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 · 254 lines · 28 tokens per session scan B fdc3fb27b15d
upgradeable-proxy is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,491 stars, last pushed 13d ago), licensed Apache-2.0. It adds 28 tokens to every session and 1,960 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). 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.