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 header-injectiongit 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/header-injection)<a href="https://agentmods.dev/skills/purpleailab/decepticon/header-injection"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/header-injection/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/header-injection"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/header-injection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 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 Supply Chain · line 127 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- medium Data Exfiltration · line 91 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 97 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 127 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 161 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 | $0.00045 | $0.02958 |
| Opus 5 | $0.00023 | $0.01479 |
| Sonnet 5 | $0.00009 | $0.00592 |
| Haiku 4.5 | $0.00005 | $0.00296 |
Grade A, and why
header-injection scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sv "${TARGET}/redirect?url=https://evil.com%0d%0aSet-Cookie:%20admin=1" 2>&1 \ How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HTTP Header Injection
Header injection turns user-controlled input into HTTP protocol control. When server code copies a request value into a response header without CR/LF stripping, an attacker can terminate the current header and inject new headers or an entire second HTTP response. At the cache layer, headers that influence the response body but are excluded from the cache key enable persistent cache poisoning. The same family of bugs drives Host-header password-reset link hijacking, X-Forwarded-For rate-limit bypass, and Content-Disposition filename injection.
Authorized use only. Only test systems you are explicitly authorized to assess. Cache poisoning attacks affect all users of a shared cache resource.
Attack Surface
- Query/body/path parameters echoed into
Location,Set-Cookie,Content-Type,Content-Disposition,Link, or customX-*headers - Request headers re-reflected into responses:
Referer,User-Agent,X-Forwarded-Host, correlation IDs - Password-reset / account-recovery flows where the reset link is built from the
Hostheader - OAuth/SSO redirect flows where
Locationis derived from user input - CDN/reverse-proxy stacks where
X-Forwarded-HostorX-Forwarded-Protois echoed into canonical URLs Content-Disposition: attachment; filename=<user_input>file-download endpoints- Outbound email headers populated from user-supplied fields (To/From/Subject)
CR/LF Injection Payload Set
These are the characters and encodings to inject. Try each until one survives to the response header:
| Encoding | Value | Notes |
|---|---|---|
| URL bare LF | %0a |
Most permissive servers |
| URL bare CR | %0d |
Rarely effective alone |
| URL CRLF | %0d%0a |
Classic; many filters strip this |
| Double-encoded | %250d%250a |
Bypasses single-decode WAFs |
| Tab | %09 |
RFC 7230 permits tab in field values; some parsers fold into preceding header |
| Null byte | %00 |
Truncates value in some C-based parsers |
| Unicode LS/PS | %e2%80%a8 / %e2%80%a9 |
U+2028/U+2029; some intermediaries fold to LF |
| Overlong UTF-8 CR | %c0%8d |
Invalid per spec but accepted by some older parsers |
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 · 230 lines · 45 tokens per session scan A fd93e3dee4a7
header-injection is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,497 stars, last pushed 13d ago), licensed Apache-2.0. It adds 45 tokens to every session and 2,958 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.