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 reportinggit 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/reporting)<a href="https://agentmods.dev/skills/purpleailab/decepticon/reporting"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/reporting/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/reporting"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/reporting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to critical
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 →
- critical YARA Match · line 368 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
- medium Privilege Escalation · line 103 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- low Privilege Escalation · line 103 Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.Fix: Request only the minimum permissions required. Document why each permission is needed. Remove broad permissions like '*' or 'all'.
- low Privilege Escalation · line 252 Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.Fix: Request only the minimum permissions required. Document why each permission is needed. Remove broad permissions like '*' or 'all'.
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 | $0.00035 | $0.05797 |
| Opus 5.5 | $0.00014 | $0.02319 |
| Sonnet 5.5 | $0.00007 | $0.01159 |
| Haiku 4.5 | $0.00003 | $0.00580 |
Grade A, and why
exploit-reporting scanned grade A 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 1mo 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Escalate privileges via local kernel or sudo misconfigurations Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -I http://10.0.1.50:8080/struts2/ | grep -i server Copies of this mod
1 near-identical copy found in the catalogue:
- exploit-reporting — 94% identical, 34 lines differ
How it starts
The opening of the file, as written. The whole thing — 465 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exploitation Reporting Knowledge Base
Exploitation findings are only operationally useful when documented with enough precision that anyone can reproduce the access, understand the impact, and trace the full attack path. This skill defines how to structure, score, and persist exploitation findings within the Decepticon engagement directory.
1. Exploitation Finding Template
Every verified successful exploitation MUST produce a finding Markdown file in the active engagement workspace's findings/ directory named FIND-{NNN}.md. The file name and id field in YAML frontmatter (FIND-001, FIND-002, ...) are the canonical cross-reference — determine the next ID by counting existing files. Do not create placeholder finding files.
---
id: FIND-001
severity: CRITICAL
cvss_score: 9.3
cvss_vector: "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N"
cwe: CWE-78
mitre: T1190
affected_target: 10.0.1.50
affected_component: "Apache Struts 2.5.30 — /struts2/upload.action"
confidence: confirmed
objective_id: OBJ-EXP-001
phase: initial-access
agent: exploit
detected: false
remediation_priority: immediate
discovered_at: "2026-04-06T14:32:00Z"
---
# [CRITICAL] Remote Code Execution via Apache Struts CVE-2023-50164 on 10.0.1.50:8080 — Root Shell Achieved
## Description
Apache Struts 2.5.30 is vulnerable to CVE-2023-50164, a file upload path traversal flaw in the `FileUploadInterceptor`. An unauthenticated attacker can manipulate the `Upload-Dir` parameter during a multipart upload request to traverse outside the intended upload directory and write an arbitrary file — including a JSP webshell — to the web root. This achieves unauthenticated remote code execution as the Tomcat service account.
The vulnerability exists because `FileUploadInterceptor` does not canonicalize the destination path before writing, allowing `../` sequences to escape the configured upload directory.
## Steps to Reproduce
```bash
# 1. Confirm the target is running Struts (identified during recon)
curl -s -I http://10.0.1.50:8080/struts2/ | grep -i server
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.
- 1mo ago First seen · 465 lines · 35 tokens per session scan A ab64efcaf5bf
exploit-reporting is a skill published in the GitHub repository PurpleAILAB/Decepticon (6,286 stars, last pushed 7d ago), licensed Apache-2.0. It adds 35 tokens to every session and 5,797 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 2 findings (asks for root, 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.
company-profile
One-page company profile slide, four quadrants of overview, financial summary, share price chart and key facts. Also the compact profile paragraph when it has to sit inside a memo, a deck or a chat reply. Triggers on one-page profile, tear sheet, company snapshot, profile slide, quick profile of [company].
idea-generation
Find long and short candidates across a universe when no name is on the table yet: mandate, universe validation, archetype screens, thematic sweep, triage, idea cards, idea log. Triggers on idea generation, stock screen, find ideas, what looks interesting, screen for, new ideas, pitch me something.
onboarding
First run after the user saves their investing profile: import holdings and watchlists from the brokerage they connected or the screenshots they attached, then propose three first tasks (one on their portfolio or watchlist, one from their profile, one on today's market) and do the one they pick.
python-lib-analyzer
Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.
research-report
A method for writing a research report, topic review, or comparison from supplied material. It separates evidence, source authors' views, and the writer's inferences while keeping sources identifiable.