Menu
SkillsMP has collected 75 skills from SpecterOps/skills. Open a skill to review its source and details.
Showing 40 of 75 collected skills.
Use when writing Outflank C2 Python BOF wrappers for OC2 V2 (*_bof.s1.py, BaseBOFTask, outflank_stage1, stage1) or V3 (oc2_sdk_python, @command, manifest.json, command provider), when porting/migrating/converting a V2 BOF script to a V3 application, or when…
Performs security review of arbitrary Go packages, including libraries, frameworks, CLIs, HTTP and gRPC services, and backend applications. Covers authentication and authorization, request parsing, SSRF, SQL and command injection, templates and filesystems,…
Develop Outflank C2 event-driven Python bots. Use when creating or debugging OC2 automations.
Use this skill when the user asks about Linux process injection, using ptrace for injection, LD_PRELOAD injection, writing to procfs, remote access via process_vm_writev, seccomp notify injection, PTRACE_POKETEXT, GOT overwrite, remote thread creation on…
Provide macOS guidance for initial access using app bundles, installer packages, and disk images, including current Gatekeeper behavior and pkgbuild and hdiutil examples.
Malleable C2 profile development for Cobalt Strike. Use when writing C2 profiles or profile overrides for Cobalt Strike.
Perform CWE-grounded security code reviews and precise weakness mapping using a locally derived MITRE CWE corpus, relationship graphs, mapping notes, detection methods, mitigations, and schema semantics. Use when Codex needs to audit source code or pull…
Perform adversarial Python security code reviews grounded in the OpenSSF Secure Coding Guide for Python. Use when Codex needs to audit large Python repositories, recovered or decompiled Python source, Python services or scripts with unclear trust boundaries,…
Perform evidence-driven security code reviews across application repositories, services, libraries, and pull requests. Use when Codex needs to audit source code for security flaws, map trust boundaries, verify authentication or authorization, trace untrusted…
Use for BloodHound Active Directory and ADCS attack-path work when the user clearly means on-prem AD semantics: find a path to Domain Admin, DA, Tier Zero, Domain Controllers, or privileged groups; investigate DCSync, ACL abuse, delegation, sessions, local…
Use as the default router for generic BloodHound asks: check the BloodHound connection, verify MCP health, analyze BloodHound data, find or explain a path, inspect shortest paths, find a path to Domain Admin or Tier Zero, show exposure, run a BloodHound…
Use when creating or changing BloodHound OpenGraph extensions, custom node schemas, custom ingestors, edge models, or Cypher patterns that connect non-AD assets to BloodHound CE graph analysis. Use for graph-model design questions such as new node kinds, new…
Use when the user explicitly wants BloodHound Cypher or query work: write a BloodHound query, review or explain Cypher, optimize a query, adapt a saved query, validate query safety or performance, convert a graph question into query syntax, or design…
Use for OpenHound collector and OpenGraph extension development work, including planning, graph schema, source collection, assets, lookup/preproc, registration, validation, and collector template adaptation under the BloodHound plugin.
Use for OpenHound GitHub/GitHound OpenGraph BloodHound work when the user clearly means GitHub semantics such as enterprises, organizations, repositories, teams, branch protection, Actions policy, secrets or variables metadata, app installations, personal…
Use for OpenHound Jamf/JamfHound OpenGraph BloodHound work when the user clearly means Jamf semantics such as Jamf tenant, site, account, group, computer, API-client exposure, Tier 1 to Tier 0 paths, policy/script/profile management privileges, traversable…
Use for OpenHound Okta/OktaHound OpenGraph BloodHound work when the user clearly means Okta semantics such as Okta users, groups, apps, role assignments, super-admin or delegated-admin exposure, API clients and client secrets, MFA or password posture, AD…
Aggressor Script development for Cobalt Strike. Use when writing aggressor scripts, creating BOF loaders, building aliases, hooks, or automation for Cobalt Strike.
Deprecated compatibility entrypoint for Cobalt Strike Aggressor references. Use cobalt-strike-aggressor-development for Aggressor, Sleep, BOF loader, and function-reference workflows.
Beacon Object File (BOF) development. Use when creating, porting, or debugging BOFs for C2 frameworks including API usage, DFR conventions, and compilation.
Provides guidance and documentation for building Mythic C2 framework agents/implants from scratch
Security-focused code review of current git changes. Use when reviewing code diffs, checking for vulnerabilities, or before merging branches.
Quick-invoke QA testing for a web app URL. Use when you want the `qa` subagent to smoke test, exercise flows, and run Lighthouse against a target URL.
Parse nmap scan output and generate actionable recon notes. Use when analyzing nmap XML/grepable output, planning service enumeration, or doing network reconnaissance.
Query Shodan for reconnaissance, target enrichment, and exposed service discovery. Builds queries, parses results, and highlights interesting findings. Requires SHODAN_API_KEY environment variable.
Clone SCCMHunter into operating-tools and install it in a local Python virtual environment using the repository's documented setup flow.
Audit a local downloaded Electron package/path or a named Electron app and produce a deep worksheet for patchability, entrypoints, and install-chain behavior. Use when deciding whether an app is a good candidate and how to modify it.
Find practical Electron apps that are likely patchable with the same Electron-plus-Squirrel method. Use when building an actionable shortlist of candidate apps rather than a broad inventory.
Preserve post-install execution and background residency for Electron apps in Squirrel-style delivery chains. Use when the payload checks in once, then dies after install or on app close.
Repackage a newer Electron app into an older Squirrel-style delivery chain while injecting a main-process payload. Use when staging a benignly named payload, hooking main.js, normalizing metadata, and regenerating RELEASES.
Generate a structured pentest finding report in markdown. Use when documenting a vulnerability, writing up a finding, or creating engagement notes.
Use for Ghostwriter MCP setup, connection verification, project discovery, oplog discovery, and environment guidance in Codex.
Use for Ghostwriter operation log entries from Codex, including config guidance, quick notes, evidence-backed entries, and guided oplog capture through the Ghostwriter MCP tools.
Parse Cobalt Strike logs into normalized timeline entries for the reporting workflow.
Merge parsed timeline entries, apply MITRE tagging, and produce the final timeline outputs.
Orchestrate the full Pentest Timeline workflow (parsers + consolidator) for reporting delivery.
Provides Binary Ninja IL documentation and MCP server usage guidance for binary analysis and reverse engineering
Draft believable copy for a credential-harvest landing page. Use when creating target-specific text for a fake login, SSO prompt, meeting join page, or internal portal notice.
Run the end-to-end phishing pretext workflow from research to final email. Use when the user has a target organization and phishing goal and wants Codex to brainstorm, refine, and produce the final email copy or HTML in one sequence.
Generate a phishing email in HTML from an approved pretext. Use when the task needs polished email copy plus HTML formatted for common delivery workflows such as GoPhish or Phishmonger.