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 verb-tamperinggit 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/verb-tampering)<a href="https://agentmods.dev/skills/purpleailab/decepticon/verb-tampering"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/verb-tampering/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/verb-tampering"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/verb-tampering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium Data Exfiltration · line 31 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 90 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 | $0.00041 | $0.02584 |
| Opus 5 | $0.00020 | $0.01292 |
| Sonnet 5 | $0.00008 | $0.00517 |
| Haiku 4.5 | $0.00004 | $0.00258 |
Grade A, and why
verb-tampering scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
code=$(curl -sk -o /dev/null -w '%{http_code} %{size_download}' -X "$m" "http://<TARGET>/admin/users") How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HTTP Verb / Method Tampering
Authorization is enforced for GET/POST but not for HEAD, OPTIONS, PATCH, DELETE, PUT, TRACE, TRACK, or arbitrary verbs like FOO. Or the app respects X-HTTP-Method-Override and the WAF/auth filter does not. Or the framework routes any verb to the same handler while only the POST ACL rule exists. Severity is High to Critical when it grants admin-only actions or reads protected data.
1. Why it works
- Apache/nginx
Limit/LimitExceptrules in.htaccessoften list onlyGET POST. Any other verb is unrestricted. - Tomcat / JSP
<security-constraint><http-method>GET</http-method>only constrains the listed verbs (the famous "Tomcat verb tampering" class — CVE-2017-12615, CVE-2009-3548 family). - API gateways enforce method-specific policies; the upstream service treats verbs identically.
- Spring
@RequestMappingwithoutmethod=accepts every verb.@GetMapping/@PostMappingconstrain, but generic mappings do not. - Express.js
app.all(path, handler)answers every method. - Framework method-override middleware (
methodOverridein Express, Rails_method=DELETE,X-HTTP-Method-Overridein many) lets aPOSTbecome aDELETEafter auth runs. - Many WAFs ship rule sets keyed on
GET/POSTonly.
2. Detection — does the endpoint answer non-standard verbs?
# Verb sweep
for m in GET HEAD POST PUT PATCH DELETE OPTIONS TRACE TRACK CONNECT PROPFIND COPY MOVE LOCK UNLOCK MKCOL FOO; do
code=$(curl -sk -o /dev/null -w '%{http_code} %{size_download}' -X "$m" "http://<TARGET>/admin/users")
printf '%-10s -> %s\n' "$m" "$code"
done
# Compare auth-required endpoint without creds, per verb
for m in GET HEAD POST PUT PATCH DELETE OPTIONS; do
curl -sk -o /dev/null -w "%-7s %{http_code}\n" -X "$m" "http://<TARGET>/admin/secret"
done
# If GET=401 but HEAD/OPTIONS=200 → verb-based auth bypass candidate.
HEAD is the highest-yield: per RFC 9110 it MUST be treated like GET minus the body, but servers diverge — middleware sometimes short-circuits auth on HEAD. Response headers and status leak data even with no body.
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.
- 6d ago First seen · 185 lines · 41 tokens per session scan A ac08b8509554
verb-tampering is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,471 stars, last pushed 10d ago), licensed Apache-2.0. It adds 41 tokens to every session and 2,584 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
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.
optimizing-ef-core-queries
Optimize Entity Framework Core queries by fixing N+1 problems, choosing correct tracking modes, using compiled queries, and avoiding common performance traps. Use when EF Core queries are slow, generating excessive SQL, or causing high database load.