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 supply-chaingit 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/supply-chain)<a href="https://agentmods.dev/skills/purpleailab/decepticon/supply-chain"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/supply-chain/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/supply-chain"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/supply-chain.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 Data Exfiltration · line 105 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 | $0.00052 | $0.01598 |
| Opus 5.5 | $0.00021 | $0.00639 |
| Sonnet 5.5 | $0.00010 | $0.00320 |
| Haiku 4.5 | $0.00005 | $0.00160 |
Grade A, and why
supply-chain scanned grade A 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
resp = requests.post(API, json={"prompt": prompt}).json()["text"] How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Supply-Chain Compromise (LLM03:2025)
An LLM product's runtime trust boundary spans far more than the
application code: pre-trained weights, fine-tune adapters, embedding
models, tokenizers, vector databases, framework packages, plugin /
MCP servers, and dataset URLs are all attacker-influenced if any of
them is sourced from a public registry. A malicious LoRA adapter or a
typo-squatted langchain-foo package is indistinguishable from a
legitimate dependency until it fires.
1. Recognition signals
- Model name is something like
-Q4_K_M.ggufpulled from HuggingFace. - Fine-tune adapter or LoRA layered on top of an open-weight base.
requirements.txt/pyproject.tomlpulls LangChain / LlamaIndex community modules from PyPI without pinning.- Plugin marketplace or MCP-server discovery feature with auto-install.
- Embedding model downloaded at startup from a CDN.
- Tokenizer files cached from an untrusted mirror.
- Continuous fine-tuning loop reads training data from a public URL.
2. Attack vectors
Backdoored weights
Trigger phrases in the prompt produce attacker-chosen output. The
model is correct on every benchmark but emits arbitrary content when
the trigger fires (e.g. "banana monkey forklift" → call an exfil tool).
Typo-squatted framework package
langchin-community, llamaindex-vector, openai-toolkit —
package names one character off from upstream that wrap the real
client and ship token-stealing code in __init__.
Compromised model registry
HuggingFace org takeover or repo rename: a model the customer pinned by name now points to attacker-controlled weights.
Malicious LoRA / adapter
Adapter advertised as "uncensored" or "improved tool-calling" actually contains the trigger backdoor + benign fine-tune mixed.
Plugin / MCP-server hijack
Plugin marketplace metadata advertises an innocuous capability; the
server emits a tool description that is itself a prompt-injection
payload (see prompt-injection skill, tool-description injection).
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.
- 1mo ago First seen · 153 lines · 52 tokens per session scan A ddd9e4a36040
supply-chain is a skill published in the GitHub repository PurpleAILAB/Decepticon (6,427 stars, last pushed 2d ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,598 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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.
company-profile
One-page company profile slide, four quadrants of overview, financial summary, share price chart and key facts. Also the compact profile paragraph when it has to sit inside a memo, a deck or a chat reply. Triggers on one-page profile, tear sheet, company snapshot, profile slide, quick profile of [company].
idea-generation
Find long and short candidates across a universe when no name is on the table yet: mandate, universe validation, archetype screens, thematic sweep, triage, idea cards, idea log. Triggers on idea generation, stock screen, find ideas, what looks interesting, screen for, new ideas, pitch me something.
onboarding
First run after the user saves their investing profile: import holdings and watchlists from the brokerage they connected or the screenshots they attached, then propose three first tasks (one on their portfolio or watchlist, one from their profile, one on today's market) and do the one they pick.
python-lib-analyzer
Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.
research-report
A method for writing a research report, topic review, or comparison from supplied material. It separates evidence, source authors' views, and the writer's inferences while keeping sources identifiable.