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 bounty-huntinggit 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/bounty-hunting)<a href="https://agentmods.dev/skills/purpleailab/decepticon/bounty-hunting"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/bounty-hunting/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/bounty-hunting"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/bounty-hunting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 133 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00037 | $0.01336 |
| Opus 5 | $0.00018 | $0.00668 |
| Sonnet 5 | $0.00007 | $0.00267 |
| Haiku 4.5 | $0.00004 | $0.00134 |
Grade A, and why
bounty-hunting-methodology 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- `exec()`, `eval()`, `spawn()`, `subprocess.run()`, `os.system()` Copies of this mod
1 near-identical copy found in the catalogue:
- bounty-hunting — 91% identical, 5 lines differ
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Bounty Hunting Methodology
You are not scanning. You are reading code, mapping architecture, and proving exploitability. Volume is the enemy — signal is the metric. Every report must survive triage by an experienced security engineer.
Target Assessment
Before committing iteration budget, evaluate the target:
- Impact surface: downloads/week, GitHub stars, dependency depth. A vuln in lodash or React Router has 10-100x the impact of a vuln in a 200-star project.
- Trust boundary complexity: Does the app load config from untrusted sources? Handle plugins? Parse user-controlled serialized data? Multi-tenant auth? Complex trust boundaries = more attack surface.
- Security advisory history: Check
github.com/advisories?query=<package>. Projects that accept and credit researchers will work with you. Projects with zero advisories are either very secure or don't have a disclosure process. - Reward program: HackerOne, Bugcrowd, Immunefi, GitHub Security Advisories, Google VRP. Check scope, excluded vuln classes, and reward tiers.
Record the assessment as a node:
kg_add_node("repo", "<name>", props={"stars": N, "downloads_weekly": N,
"has_security_policy": true, "advisory_count": N, "bounty_program": "hackerone"})
White-Box Methodology
This is the core loop. Fork. Read. Trace. Prove.
Step 1 — Map the project
find /workspace/target -name 'package.json' -o -name 'pyproject.toml' \
-o -name 'go.mod' -o -name 'Cargo.toml' -o -name 'composer.json' | head -20
Identify: language, framework, entry points, config loading, auth middleware.
Step 2 — Map trust boundaries
Where does untrusted input enter the system? Trace these sources:
- HTTP request params, headers, body
- Environment variables and
.envfiles - Config files from current directory (
.gemini/settings.json,.vscode/settings.json) - Plugin/extension loading paths
- Deserialization of user-controlled data (pickle, YAML, JSON with class hints)
- IPC channels, WebSocket messages, MCP tool inputs
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 · 134 lines · 37 tokens per session scan A fb299373e76b
bounty-hunting-methodology is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,491 stars, last pushed 13d ago), licensed Apache-2.0. It adds 37 tokens to every session and 1,336 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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.