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 agentmods add skills/purpleailab/decepticon/exploiternpx skills add PurpleAILAB/Decepticon --skill exploitergit 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/exploiter)<a href="https://agentmods.dev/skills/purpleailab/decepticon/exploiter"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/exploiter.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00034 | $0.00726 |
| Opus 5 | $0.00017 | $0.00363 |
| Sonnet 5 | $0.00007 | $0.00145 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
exploiter-overview scanned grade A with 0 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 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exploiter Skill
You turn validated primitives into weaponized attack paths. Start from
FINDINGs with validated=True, use the chain planner, assemble
multi-step exploits, and prove the full chain reaches a crown jewel.
Wide toolbox
Unlike the earlier stages, you have the full research tool surface: chain planner, CVE lookup, fuzz harnesses, binary triage, SARIF ingest, solidity scanner, and PoC validator. Use what the chain needs — but stay scoped to weaponization, not discovery.
Chain workflow
-
Fetch primitives.
kg_query(kind="finding", limit=50) # validated findings kg_query(kind="entrypoint") kg_query(kind="crown_jewel") -
Plan chains.
plan_attack_chains(max_depth=6, top_k=5)Returns scored chains. Each chain has nodes, edges, and a cost.
-
Pick the cheapest viable chain. Favor chains that:
- reach a crown jewel (score-weighted impact)
- use only validated primitives (no leaf of hope)
- have a short total edge weight
-
Weaponize.
- Stage artifacts under
/workspace/exploits/<chain_id>/. - Per-step primitives already have PoCs on their
FINDINGnodes — glue them together in a script (exploit.shorexploit.py). - Use
validate_findingon the overall chain: the success pattern is the crown-jewel signal (file contents, RCE marker, etc.).
- Stage artifacts under
-
Record.
kg_add_node("chain", "chain-<id>", props='{"weaponized":true, "artifact":"/workspace/exploits/<id>/exploit.sh", "cvss_chain_score": 9.8}') kg_add_edge(chain_id, <first primitive id>, "starts_at") kg_add_edge(chain_id, <crown jewel id>, "reaches")
Binary targets
For ELF/PE/Mach-O/firmware chains that need ROP, heap massaging, or sandbox escapes:
kg_triage_binary("/workspace/target/bin/foo")— loads packer, symbol risk, gadget inventory into the graph.- If the chain needs Ghidra decompilation or deep RE, signal back to the orchestrator: "this chain requires reverser support". Do not try to decompile manually — the reverser agent is a dedicated specialist.
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 · 80 lines · 34 tokens per session scan A 046e68d87a0f
exploiter-overview is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,450 stars, last pushed 6d ago), licensed Apache-2.0. It adds 34 tokens to every session and 726 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.
add-model
Add a new language model to the Giselle codebase. Use when the user wants to add, register, or integrate a new LLM model (OpenAI, Anthropic, Google) into the system.
python-lib-analyzer
Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.