Autonomous Hacking Agent for Red Team
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.
Skill Claude Code needs its repo
YARA rule writing from behavioral observations and TI report analysis — sample-to-rule conversion, condition optimization, performance tuning, and retrohunting on VirusTotal and ANY.RUN. Covers YARA/YARA-X syntax, yarGen automated generation, and production rule deployment.
Skill Claude CodeCodex
Trust boundary mapping and startup sequence audit for developer tools, CLI apps, and plugin systems. Load when the target is a developer tool, CLI, IDE extension, or any application that loads config from the current directory.
Skill Claude CodeCodex
Hunt LLM unbounded consumption (OWASP LLM10:2025) — denial-of-wallet and denial-of-service against LLM endpoints via unrestricted prompt size, runaway tool loops, expensive model selection, and unauthenticated fan-out.
Skill Claude CodeCodex
Hunt vector / embedding weaknesses (OWASP LLM08:2025) — adversarial inputs against the RAG / similarity layer that cause cross-tenant leak, embedding-inversion privacy loss, semantic confusion, and retriever-driven prompt injection.
Skill Claude CodeCodex
Hunt XML External Entity flaws in parsers and validate file read / SSRF impact with strict negative controls.
Skill Claude CodeCodex
Cloud exploitation lane — AWS IAM privesc, S3 takeover, k8s RBAC abuse, Terraform state leaks, cloud metadata pivoting.
Skill Claude CodeCodex
Enumerate AWS IAM policies, detect privilege escalation paths per Rhino Security Labs canonical 21 primitives.
Skill Claude Code
AWS IAM privilege escalation via iam:PassRole chains — Lambda/Glue/Sagemaker/EC2/ECS PassRole to a higher-priv role, AssumeRole chains across accounts, sts:GetCallerIdentity recon, account hijack via legacy root-mfa-bypass.
Skill Claude Code
Azure Managed Identity abuse — IMDS at 169.254.169.254 from compromised VM / App Service / Function, token exchange for Graph/ARM/KeyVault, federated workload identity abuse, hybrid AAD Connect MSOL credential extraction.
Skill Claude Code
Container / Kubernetes attack category — pod escape, RBAC abuse, runtime CVE exploitation, socket-mount escape. Routing skill: identify the surface (pod-internal RCE vs API-level vs build-pipeline), then load the matching sub-skill.
Skill Claude Code
High-impact container-runtime CVE catalog — runC Leaky Vessels (CVE-2024-21626/-23651/-23652/-23653), CVE-2022-0185 (FUSE/legacy-fs), CVE-2019-5736 (runC binary replace), CRI-O Dirty COW analogs, Kubernetes API server CVE-2019-11247 (custom-resource RBAC bypass). Fingerprint → match → exploit.
Skill Claude Code
Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.
Skill Claude Code
Kubernetes pod escape to node — privileged container abuse, hostPath mount escape, hostPID/hostIPC, capability misuse (SYSADMIN, SYSPTRACE), runC CVE chains. Pivots from RCE-in-pod to full node compromise.
Skill Claude Code
Kubernetes RBAC privilege escalation paths — ClusterRole/Role enumeration via kubectl auth can-i --list, abuse of pods/exec, pods/portforward, secrets get, escalate verb, bind verb, impersonate verb, system:masters group abuse, ServiceAccount token theft and reuse.
Skill Claude Code
Entra Conditional Access bypass — discover policy gaps, exploit legacy-auth protocols (IMAP/POP/SMTP-AUTH/EWS), spoof device/platform/UA/location conditions, abuse service-principals + app-based auth excluded from CA, and break-glass account misuse.
Skill Claude Code
Entra ID OAuth device-code phishing for token theft, illicit consent grant via malicious app registration with delegated Graph scopes, refresh-token replay, and primary-refresh-token (PRT) abuse concepts.
Skill Claude Code
Entra ID / M365 reconnaissance — unauthenticated tenant discovery via OpenID config, GetUserRealm, autodiscover; user enumeration via login response codes and OneDrive; federation/MFA/CA posture; authenticated enumeration with ROADtools (roadrecon), AADInternals, MSGraph.
Skill Claude Code
Entra ID privilege escalation + persistence — app role/owner abuse, service-principal credential addition, dynamic group membership abuse, Administrative Unit role assignment, hybrid identity attacks (Connect, PHS, PTA, Seamless SSO, Golden SAML), Graph API privesc paths.
Skill Claude CodeCodex
GCP organization-level privilege escalation — cross-project pivoting, org policy bypass, service account impersonation chains, Terraform state secrets, and GKE cluster compromise. Escalate from single-project access to org-wide control.
Skill Claude Code
GCP service account impersonation chain — IAM roles/iam.serviceAccountTokenCreator, roles/iam.serviceAccountUser, actAs on Cloud Functions / Cloud Run / Compute Engine. Pivot from low-priv SA to org-admin via chained impersonation.
Skill Claude CodeCodex
Pivot from SSRF or RCE to cloud Instance Metadata Service (IMDS) — extract IAM role creds, instance identity, user-data secrets.
Skill Claude CodeCodex
Kubernetes attack playbook — service-account token theft, RBAC abuse, pod escape, hostPath mount abuse, kube-api-server pivoting.
Skill Claude CodeCodex
Microsoft 365 mailbox compromise chain — OAuth consent phishing, delegate access abuse, mail rule persistence, and token theft via device code phishing. Full kill chain from initial access to persistent email collection.
Skill Claude CodeCodex
Detect and claim dangling S3 buckets referenced by subdomains (CNAME → s3 hostnames where bucket no longer exists).
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: