Agent Skills by PurpleAILAB
There are 7 agent skills in our directory.
PurpleAILAB publishes 7 AI agent skills in our directory. Browse them below — each links back to its source repository.
Updated June 2026
- aatmf-t05-api-exploitationAATMF T5 — Model & API Exploitation. Rate-limit abuse, token-cost amplification, schema bypass, model-version manipulation.
- audit>
- c2-alternative-channelsNon-traditional C2 channels — Discord/Telegram bots, DNS-over-HTTPS, blockchain-based C2, email-based C2, and cloud function dead drops for covert command and control.
- contracts-governance-attackDAO governance attack — flash-loan-backed vote manipulation, delegation hijack, quorum dilution, proposal-spam DoS, time-lock bypass via emergency multisig, snapshot vs. on-chain vote desync, Compound/Aave/Uniswap-style GovernorBravo abuse.
- defense-evasionEndpoint defense bypass — AMSI/ETW patching, ScareCrow framework, custom loaders, direct/indirect syscalls, LOLBAS execution, process injection.
- volt-typhoonAdversary-emulation profile for Volt Typhoon (G1017), a PRC state-sponsored actor pre-positioning in US critical infrastructure via living-off-the-land TTPs.
- web-waf-detectionWeb Application Firewall fingerprinting — Cloudflare, AWS WAF, Akamai, Imperva, etc.