powerquery

powerquery is a Blue team & detection skill for AI agents, published by Sentinel-One in the ai-siem repository on GitHub. Skillspace rates powerquery C (70/100) and it passed the safety scan; the rating is based on static analysis only.

Use any time the user wants to author, debug, optimize, explain, or run a SentinelOne PowerQuery (PQ) — Deep Visibility / Event Search queries, XDR/EDR threat hunting, investigations, STAR / Custom Detection rule bodies, PowerQuery Alerts, or Singularity Data Lake dashboard panels. Trigger on PowerQuery, PQ, pq, query, Event Search, Deep Visibility, S1QL, SDL, STAR rule, Custom Detection rule, PowerQuery Alert; on queries using fields like `event.type`, `src.process.*`, `tgt.file.*`, `indicator.*`, `agent.uuid`; on pipes like `| group`, `| filter`, `| let`, `| join`, `| parse`, `| columns`, `| compare`, `| top`, `| union`, `| lookup`, `| savelookup`, `| dataset`. Also trigger when asked to hunt a TTP, IOC, behaviour, or alert pattern on a SentinelOne tenant — even casually ("find powershell reaching out to the internet", "write a detection for lsass access"). Explicitly NOT Microsoft Power Query / M / Excel and NOT Splunk SPL — this is SentinelOne's pipeline query language for security…

Grade
C
Quality
70 / 100
Safety
Passed
GitHub stars
51

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Our review

Architecture
100 / 100
Maturity
Structured: ships references or scripts
Security scan
Low-risk patterns
License
AGPL-3.0
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • mentions secrets in text

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.