Menu

Individual skill

bloodhound-query

0upvotes

Analyze authorized AD collection data in BloodHound CE with the active runtime's supported tools and mirrored GUI.

packages/decepticon/decepticon/skills/standard/ad/bloodhound-query/SKILL.md

Read pinned source

Source commit df879550544d36b6b1e69062f05adae28537adf2

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
Yes
Observed behavior
Instructions only
Last checked
Nov 9, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
6,576
Repository last updated
Nov 9, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# BloodHound analysis

BloodHound analyzes collected AD data; discovering a domain or opening its viewer does not populate the graph. Work only with the authorized domain and an existing collection path. Report missing collection access rather than claiming an empty graph proves safety.

## Hosted engagement

1. Use the engagement-isolated BloodHound CE companion. If a compatible SharpHound ZIP already exists under `/workspace`, call `bloodhound_mcp_upload_collection(path=...)`. Check that the returned terminal status is `Complete`; report partial or failed ingest.
2. If no ZIP exists, collect only through an authorized foothold and transfer its ZIP to `/workspace`. Alternatively, where a scoped DC is reachable and a Kerberos cache exists in `/workspace`, use `bloodhound_mcp_collect_domain` with the matching domain, DC, username, and cache. Begin with `DCOnly`; `Default` and `Session` require an explicit computer allowlist. Never pass passwords or hashes as MCP arguments.
3. After a completed upload, check `bloodhound_mcp_data_quality` and `bloodhound_mcp_domain_overview`. Use `bloodhound_mcp_find_objects` and `bloodhound_mcp_object_profile` for specific principals; `bloodhound_mcp_exposure_finder` and `bloodhound_mcp_shortest_path` for bounded questions. Use `bloodhound_mcp_cypher_query` only when semantic tools cannot answer a read-only question. Bound returned rows and path depth.
4. Check GUI follow status before claiming that the operator can see the selected object or path. Distinguish a candidate graph path from an action proven by independent evidence. Record confirmed results through the active engagement's finding and OPPLAN tools.

The hosted MCP graph is separate from any standalone BloodHound instance. Do not call `bhce_*`, `bh_ingest_zip`, `bh_cypher`, or a local `cypher-shell` for hosted analysis.

## Standalone OSS runtime
Back to top