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 waf-bypassgit 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/waf-bypass)<a href="https://agentmods.dev/skills/purpleailab/decepticon/waf-bypass"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/waf-bypass/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/waf-bypass"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/waf-bypass.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, 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 Privilege Escalation · line 54 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Data Exfiltration · line 48 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 178 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 | $0.00048 | $0.03846 |
| Opus 5 | $0.00024 | $0.01923 |
| Sonnet 5 | $0.00010 | $0.00769 |
| Haiku 4.5 | $0.00005 | $0.00385 |
Grade A, and why
waf-bypass 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sI "https://<TARGET>/?id=1' OR '1'='1" | grep -iE 'server|cf-ray|x-amzn|akamai|x-sucuri|x-cdn|set-cookie' How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WAF Bypass / Evasion
A WAF is a signature + score engine in front of the origin. Bypass goals: (a) deliver a payload the rule set does not match, (b) reach the origin directly so the WAF is out of band, or (c) keep request rate / anomaly score under thresholds while exfiltrating. OPSEC: this skill is for authorized scope. Stay within rate limits the program allows; never test live customer flows; mark traffic with a researcher header where the program asks for it (X-Bug-Bounty: <HANDLE>).
1. Recon first — fingerprint the WAF
See skills/standard/recon/web-recon/waf-detection/SKILL.md. Without a fingerprint you are guessing. Quick:
wafw00f -a "https://<TARGET>"
curl -sI "https://<TARGET>/?id=1' OR '1'='1" | grep -iE 'server|cf-ray|x-amzn|akamai|x-sucuri|x-cdn|set-cookie'
nuclei -u "https://<TARGET>" -t http/technologies/waf-detect.yaml
Note the stack: WAF vendor, CDN, origin web server, application framework. Each layer has its own parser — bypasses live in the gaps.
2. Payload obfuscation
| Layer | Technique | Example |
|---|---|---|
| Case | Mixed case on keywords (most modern WAFs are case-insensitive — try anyway) | SeLeCt, uNiOn |
| Whitespace | Tab, FF, CR, LF, /**/, +, %a0, %0b, %0c between tokens |
UNION/**/SELECT, UNION%a0SELECT |
| Comments | Inline SQL comments split keywords | UN/**/ION, SEL/*!50000*/ECT (MySQL versioned) |
| Encoding | URL-encode, double-URL-encode, unicode, HTML entity, base64 | %2527, %u0027, ', \x27, \u0027 |
| Mixed encoding | Encode only the bytes the rule looks for | '%20OR%201=1-- → %27 OR 1%3D1-- |
| Alternate syntax (SQL) | UNION-less extraction via boolean/blind, ` |
|
| Alternate syntax (XSS) | Tagless / event-less / template / SVG / MathML | <svg/onload=alert(1)>, <details/open/ontoggle=alert(1)>, <style>@import"//x"</style> |
| String concat | Break signatures into pieces | '+'al'+'ert'+'(1)+', concat(0x61,0x64,0x6d,0x69,0x6e) |
| Backtick / quote variants | `select`, "select", [select] (MSSQL), N'admin' |
|
| Null bytes | %00 early-terminates many string ops in C-backed parsers |
admin%00.png |
| Charset | Submit body in unusual charset; WAF inspects as UTF-8 but app decodes UTF-16 | Content-Type: ...; charset=utf-16le |
| Path normalization | ..;/, ..%2f, ..%252f, ;/, // between segments |
/admin..;/users |
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 · 240 lines · 48 tokens per session scan A f0ddd4728fa7
waf-bypass is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,497 stars, last pushed 13d ago), licensed Apache-2.0. It adds 48 tokens to every session and 3,846 once invoked, about $0.0002 per session on Opus 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.
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.