An open agent-skills library for malware analysis, reverse engineering, and threat hunting - 118 curated, runnable skills mapped to MITRE ATT&CK, D3FEND, and CAR.
This repository also configures its own agents. See what analyst-ai-pack tells them →
Skill Claude CodeCodex
Analyzes bootkit and rootkit samples by identifying boot-process tampering (MBR/VBR/ UEFI), kernel-mode components, and stealth hooking techniques from static indicators. Activates for requests to analyze a bootkit or rootkit, examine MBR/UEFI tampering, or identify kernel-mode stealth components.
Skill Claude CodeCodex
Rebuilds a usable PE file from a memory dump by fixing the section alignment (virtual-to-raw), correcting the entry point, and preparing for import table reconstruction. Activates for requests to rebuild a dumped PE, fix a memory-dumped executable, or convert a process dump into an analyzable file.
Skill Claude CodeCodex
Emulates position-independent shellcode in a controlled CPU emulator (Unicorn) to trace executed instructions, memory writes, and decoded second stages without running it on a real host. Activates for requests to emulate shellcode, trace a decoder stub, or recover a stage unpacked at runtime by shellcode.
Skill Claude CodeCodex
Enriches indicators with context from threat-intel sources: planning lookups against reputation, passive DNS, WHOIS, and sandbox/sample databases, scoring confidence, and avoiding operational-security mistakes that tip off adversaries. Activates for requests to enrich IOCs, add threat context, or plan indicator…
Skill Claude CodeCodex
Establishes behavioral baselines from historical telemetry (process, network, or logon events) so hunts can flag rare and first-seen activity instead of relying on static signatures. Activates for requests to build a telemetry baseline, find rare or first-seen activity, or compute frequency baselines for anomaly…
Skill Claude CodeCodex
Extracts ASCII and Unicode strings from a binary and classifies them into investigative categories: URLs, IPs, file paths, registry keys, mutexes, commands, and API names, prioritizing the analyst's attention. Activates for requests to extract strings, classify strings output, or pull human-readable artifacts from a…
Skill Claude CodeCodex
Extracts and interprets a Cobalt Strike Beacon configuration: decoding the encoded config block, recovering C2 servers, malleable profile fields, sleep/jitter, watermark, and pipe names to build IOCs and attribution leads. Activates for requests to analyze a Cobalt Strike beacon, extract beacon config, or interpret…
Skill Claude CodeCodex
Extracts an embedded malware configuration (C2 hosts, ports, campaign IDs, keys) from a process memory dump by locating decrypted config structures and decoding common obfuscation layers. Activates for requests to extract malware config from a memory dump, recover C2 settings from a running sample, or decode an…
Skill Claude CodeCodex
Locates candidate encryption keys in a binary by finding high-entropy fixed-size regions (16/24/32 bytes) near cryptographic constants or crypto API references, and surfacing printable key/passphrase strings. Activates for requests to extract encryption keys, find an AES key in a sample, or recover hardcoded crypto…
Skill Claude CodeCodex
Extracts indicators of compromise from raw analysis artifacts: parsing strings dumps, sandbox reports, PCAP summaries, and logs for URLs, domains, IPs, hashes, mutexes, and file paths, then deduplicating and typing them. Activates for requests to extract IOCs from analysis output, pull indicators from a report, or…
Skill Claude CodeCodex
Uses capa to identify malware capabilities from a binary: running rule-based detection over disassembly, mapping matched capabilities to MITRE ATT&CK and MBC, and interpreting results to focus deeper analysis. Activates for requests to run capa, generate a capability report, or map a sample's behaviors to ATT&CK…
Skill Claude CodeCodex
Establishes safe practices for acquiring, storing, transferring, and disposing of malware samples: password-protected archives, neutralized extensions, hashing for identity, and chain-of-custody. Activates for requests about safely storing or sharing malware, sample handling hygiene, or defanging artifacts.
Skill Claude CodeCodex
Computes cryptographic and fuzzy fingerprints for malware samples: MD5/SHA-1/SHA-256 for exact identity, plus import hashing (imphash), section hashing, and fuzzy hashes (ssdeep, TLSH) to cluster related variants. Activates for requests to hash a sample, compute imphash, or fingerprint files for similarity clustering.
Skill Claude CodeCodex
Hunts for Active Directory credential and replication attacks — DCSync, Golden/Silver Ticket, and DCShadow — by analyzing directory-service-access (4662), Kerberos TGS (4769), and logon (4624) events for replication abuse and forged-ticket anomalies. Activates for requests to hunt DCSync, detect golden/silver tickets…
Skill Claude CodeCodex
Hunts for anomalous authentication such as password spraying, brute force, and impossible-travel logons by aggregating Windows logon success/failure events per account and source over time. Activates for requests to hunt anomalous logons, detect password spraying or brute force, or find suspicious authentication…
Skill Claude CodeCodex
Detects command-and-control beacons in network logs by analyzing connection timing: measuring inter-arrival intervals, accounting for jitter, and scoring regularity per source/destination pair to surface periodic callbacks. Activates for requests to hunt C2 beaconing, find periodic callbacks, or analyze…
Skill Claude CodeCodex
Hunts for Cobalt Strike beacon traffic by detecting default stager URI checksum8 values, default Malleable C2 profile artifacts, and default ports/named pipes in HTTP and process telemetry. Activates for requests to hunt Cobalt Strike, detect beacon stager URIs, or find default Malleable C2 indicators.
Skill Claude CodeCodex
Hunts for credential dumping by detecting LSASS process access with suspicious access masks, known dumping tool signatures, and comsvcs.exe MiniDump abuse in Sysmon Event ID 10 and process-creation telemetry. Activates for requests to hunt credential dumping, detect LSASS access, or find Mimikatz/comsvcs MiniDump…
Skill Claude CodeCodex
Hunts for pre-exfiltration data staging and archiving by detecting archive-tool execution (rar, 7z, zip, tar), large compressed files written to staging directories, and collection into a single location before transfer. Activates for requests to hunt data staging, detect pre-exfil archiving, or find collection and…
Skill Claude CodeCodex
Detects DNS-based tunneling and data exfiltration in DNS logs: scoring high query volume to single domains, long/high-entropy subdomains, unusual record types, and encoded payload labels. Activates for requests to hunt DNS tunneling, detect DNS exfiltration, or analyze suspicious DNS query patterns.
Skill Claude CodeCodex
Hunts for domain fronting and CDN abuse by detecting TLS SNI versus HTTP Host header mismatches and high-reputation CDN domains carrying anomalous traffic in network telemetry. Activates for requests to hunt domain fronting, detect SNI/Host mismatch, or find CDN abuse used to mask C2.
Skill Claude CodeCodex
Hunts for fileless and in-memory threats by correlating PowerShell script-block logs, encoded-command usage, in-memory loading patterns, and registry-resident payloads from Windows telemetry. Activates for requests to hunt fileless malware, detect in-memory execution, or find registry-resident and reflective-loading…
Skill Claude CodeCodex
Operationalizes a threat intelligence report into hunts: extracting IOCs and TTPs, mapping behaviors to ATT&CK and available telemetry, prioritizing durable behavioral indicators over volatile atomic ones, and producing concrete hunt queries. Activates for requests to hunt from a threat report, operationalize CTI, or…
Skill Claude CodeCodex
Hunts for Kerberoasting and related ticket attacks by analyzing Kerberos service ticket request events (4769) for weak encryption types, abnormal request volume per account, and non-machine accounts requesting many SPNs. Activates for requests to hunt Kerberoasting, detect RC4 ticket requests, or find SPN-targeting…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: