BloodHound CE runtime selection and collection analysis for hosted MCP or standalone OSS tools.
74%
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
Fix and improve this skill with Tessl
tessl review fix ./packages/decepticon/decepticon/skills/standard/ad/bloodhound-bhce/SKILL.mdFirst identify which BloodHound tools the active agent actually has. The hosted engagement uses its own isolated bloodhound_mcp_* companion and live GUI; standalone OSS may expose bhce_* tools for a different local instance. Never mix their data or credentials. Load /skills/standard/ad/bloodhound-query/SKILL.md only when its detailed procedure is relevant; the path is not an automatic prerequisite.
In hosted runs, bloodhound_mcp_upload_collection ingests an authorized ZIP under /workspace. Verify terminal Complete, then use bloodhound_mcp_data_quality, bloodhound_mcp_domain_overview, bloodhound_mcp_find_objects, bloodhound_mcp_object_profile, bloodhound_mcp_exposure_finder, and bloodhound_mcp_shortest_path. Use bloodhound_mcp_cypher_query only for bounded read-only questions. The resulting GUI follow status is evidence that the remote viewer moved; opening the viewer by itself does not collect or analyze AD data.
In standalone OSS, when bhce_* tools are actually registered, use bhce_status to check the local instance, bhce_ingest_zip to import a compatible collection, and bhce_cypher to inspect its graph. The retired in-house bh_ingest_zip and related wrappers are deprecated. Do not assume a fixed BloodHound version or schema; use the actual instance's reported capabilities.
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.