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 samlgit 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/saml)<a href="https://agentmods.dev/skills/purpleailab/decepticon/saml"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/saml/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/saml"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/saml.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Prompt Injection · line 38 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00040 | $0.01429 |
| Opus 5 | $0.00020 | $0.00714 |
| Sonnet 5 | $0.00008 | $0.00286 |
| Haiku 4.5 | $0.00004 | $0.00143 |
Grade A, and why
saml scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- saml — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAML Attack Playbook
SAML is XML-based SSO used heavily in enterprise. Signatures protect assertions but XML's structural flexibility creates many opportunities to confuse signature validators.
1. Capture the flow
# Identify SAML in recon — look for:
# - /SAML/login, /sso/saml, /saml2/login
# - Form param "SAMLRequest" or "SAMLResponse" (base64 + deflate)
# - SP metadata: /SAML/metadata, /sp/metadata.xml
# - IdP metadata: /idp/metadata.xml
# Decode a SAML message in Burp via the SAML Raider plugin
# Or manually
echo "$SAMLResponse_base64" | base64 -d | xmllint --format -
2. XML Signature Wrapping (XSW) attacks
The classic SAML bug class. 8 canonical variants. SAML Raider implements all of them.
XSW1: Wrap signed Assertion inside Response, add evil assertion
<Response>
<ds:Signature>...</ds:Signature> <!-- signs the inner Assertion -->
<Assertion id="evil">
<Subject>attacker</Subject>
<AttributeStatement>...</AttributeStatement>
</Assertion>
<!-- original signed assertion moved into a deeper child or as sibling of evil -->
<Assertion id="orig">
<Subject>victim</Subject>
...
</Assertion>
</Response>
Parser-checks-signature on orig (still valid). App-reads-claims from
evil (first assertion). Bypass complete.
XSW2-8
Vary which element is signed, what gets added where, what gets renamed. Run all 8 via SAML Raider's automated XSW tester.
3. Comment injection
SAML libraries that strip XML comments BEFORE signature validation but the application reads the un-stripped version (or vice versa):
<Subject>[email protected]<!-- foo -->.evil.com</Subject>
Some parsers see [email protected]; others see [email protected].
Famous: Cisco DUO + others in 2018 (CVE-2018-0489).
4. Signature stripping
Just delete the <ds:Signature> element. Some servers fail to enforce
signature presence.
5. Self-signed assertion (when allowed by misconfig)
Some SPs accept assertions from any IdP listed in their trust store. If the trust store is overly broad, attacker stands up own IdP, generates own cert, IdP signs assertion claiming victim identity.
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 · 146 lines · 40 tokens per session scan A de22e63c1166
saml is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,491 stars, last pushed 13d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,429 once invoked, about $0.0002 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
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.