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 deserializationgit 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/deserialization)<a href="https://agentmods.dev/skills/purpleailab/decepticon/deserialization"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/deserialization/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/deserialization"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/deserialization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Data Exfiltration · line 115 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 144 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00062 | $0.01381 |
| Opus 5 | $0.00031 | $0.00691 |
| Sonnet 5 | $0.00012 | $0.00276 |
| Haiku 4.5 | $0.00006 | $0.00138 |
Grade B, and why
deserialization scanned grade B with 3 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -X POST https://target.com/api/import -H "Content-Type: application/x-java-serialized-object" --data-binary @payload.set Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST https://target.com/api/import -H "Content-Type: application/x-java-serialized-object" --data-binary @payload.set Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
def __reduce__(self): return (os.system, ("id > /tmp/pwn",)) Copies of this mod
1 near-identical copy found in the catalogue:
- deserialization-analysis — 89% identical, 5 lines differ
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Insecure Deserialization Playbook
Deserialization is the single most reliable path from a byte string under user control to unauthenticated remote code execution. Modern frameworks have tried to wall this off, but chained-gadget attacks (ysoserial, ysoserial.net, marshalsec, phpggc) still make this a top-tier finding.
1. Sources (user-controlled data that becomes an object)
- HTTP body, cookie, header, query param
- Message queue payload (Kafka, RabbitMQ, SQS)
- File upload parsed as config
- WebSocket messages
- Inter-service RPC
2. Dangerous sinks by language
Python
pickle.loads/pickle.load/pickle.Unpicklerdill.loads,cloudpickle.loads,shelve.openyaml.load()withoutLoader=SafeLoaderjsonpickle.decodenumpy.load(allow_pickle=True)torch.load(loads pickled tensors → RCE)joblib.loadmarshal.loads
grep -rE 'pickle\.loads?\(|yaml\.load\([^)]*Loader=(FullLoader|Loader)?\)|torch\.load\(' /workspace/src
semgrep --config p/insecure-transport --config p/python /workspace/src -o /workspace/sem-deser.sarif
Java
ObjectInputStream.readObjectXMLDecoder.readObjectJackson ObjectMapperwith default typing + polymorphic typesSnakeYAMLYaml.load()(before 2.0) — RCE via!!javax.script.ScriptEngineManagerXStreamwithout whitelistHessian,Kryowith registration disabled
Gadgets: ysoserial payloads (CommonsCollections, Spring, Groovy, C3P0)
.NET
BinaryFormatter.Deserialize(deprecated but still common)SoapFormatter,LosFormatter,ObjectStateFormatterJavaScriptSerializerwithSimpleTypeResolverJson.NETwithTypeNameHandling != None
PHP
unserialize()on any user input- PHAR uploads —
file_exists("phar://upload.phar")triggers deser - Laravel
decrypt()→unserialize(pre-patched APP_KEY leak chain)
Ruby
Marshal.loadYAML.load(before Psych 4 safe default)Oj.loadwithoutmode: :rails
Node.js
node-serializeunserialize()serialize-to-jsdeserialize()vm.runInNewContext(userInput)— not technically deser but same impact
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 · 149 lines · 62 tokens per session scan B 56e7652efc23
deserialization is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,471 stars, last pushed 10d ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,381 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 3 findings (sends data to an external url, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
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.
idea-generation
Stock screening and idea generation: quantitative screens, thematic analysis, shortlist.
secretary
Workspace and research management — dispatch analyses, monitor running agents, manage workspaces and threads.
python-lib-analyzer
Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.
analyzing-windows-prefetch-with-python
Use when parse Windows Prefetch files using the windowsprefetch Python library to reconstruct application execution history, detect renamed or masquerading binaries, and identify suspicious program execution patterns. Use when working with analyzing windows prefetch with python.