Analyze authorized AD collection data in BloodHound CE with the active runtime's supported tools and mirrored GUI.
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
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.
/workspace, call bloodhound_mcp_upload_collection(path=...). Check that the returned terminal status is Complete; report partial or failed ingest./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.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.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.
If the hosted MCP tools are absent and the standalone bhce_* tools are registered, use bhce_status to check the local instance, bhce_ingest_zip for a compatible ZIP, and bhce_cypher for bounded read-only queries. Never treat data from another instance as the current engagement's collection.
PurpleAILAB/Decepticon
98e51d3
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.