meltedinhex/analyst-ai-pack / skills/hunting-suspicious-powershell-execution
hunting-suspicious-powershell-execution
VerifiedHunts malicious PowerShell using script-block (EID 4104) and module logging: scoring encoded commands, download cradles, AMSI/logging bypass, and in-memory execution, then decoding payloads for triage. Activates for requests to hunt malicious PowerShell, analyze script-block logs, or detect encoded command abuse.
Hunting Suspicious PowerShell Execution
When to Use
- You have PowerShell script-block (Event ID 4104) and/or module logging and want to hunt abuse.
- You are testing a hypothesis that attackers use encoded commands, download cradles, or AMSI/logging bypasses.
- You need to score and decode a large volume of PowerShell events into a triage queue.
Do not use simple keyword blocklists as the sole method — admins legitimately use many of the same cmdlets; score combinations and decode before judging.
Prerequisites
- Script-block logging enabled (Event ID 4104) and exported to a queryable store.
- A baseline of normal administrative PowerShell for your environment.
Workflow
Step 1: Collect script-block events
Pull EID 4104 script-block text (and EID 4103 module logging) over the hunt window. Reassemble multi-part script blocks before analysis.
Step 2: Score suspicious constructs
Weight combinations rather than single keywords: -EncodedCommand, IEX/Invoke-Expression
with Net.WebClient/Invoke-WebRequest, FromBase64String, -w hidden -nop, AMSI strings,
and [Ref].Assembly reflection.
python scripts/analyst.py score events.json
Step 3: Decode payloads
Base64-decode -EncodedCommand (UTF-16LE) and recover layered encodings to read the real
intent (download URLs, in-memory loaders).
Step 4: Baseline and pivot
Compare against normal admin activity; for survivors, pull the parent process, user, host, and network connections to confirm.
Step 5: Confirm and operationalize
Validate true positives, escalate to IR, and convert the scoring logic into a detection rule.
Validation
- High-score events decode to coherent malicious intent, not benign admin scripts.
- Multi-part script blocks are reassembled before scoring (no truncated false negatives).
- Confirmed cases tie to a parent process and user consistent with intrusion.
Pitfalls
- Flagging single keywords (
IEXalone) and drowning in admin noise. - Forgetting
-EncodedCommandis UTF-16LE, producing garbled decodes. - Ignoring AMSI/logging-bypass attempts that precede the real payload.
References
- See
references/api-reference.mdfor the scorer/decoder. - Script-block logging docs and ATT&CK T1059.001 (linked in frontmatter).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |