ai-security agents

DinoMorphica/safeclaw

Agent Claude Code

You are a specialist agent for publishing the safeclaw npm package. Follow these instructions exactly.

DinoMorphica/safeclaw

Agent Claude Code

The Skill Scanner provides proactive, pre-execution security analysis of markdown skill definitions. While SafeClaw's runtime Threat Analysis Engine (TC- categories) classifies activities as they happen, the Skill Scanner inspects skill files before\ they're loaded — catching hidden threats that are invisible to human…

Mikaru0Mystic/sectinel

Agent

You have a local arsenal of 784 cybersecurity skills (agentskills.io standard) installed at /.config/opencode/cybersec-arsenal/. When a security task appears (audit, threat model, vulnerability research, secrets, IaC, cloud, API, incident response, red or blue team, AI/LLM security, compliance), do not improvise. Find…

friedbotstudio/baseline

Agent Claude Code

Execute a single swarm task in an isolated git worktree. Receive a fully-specified recipe from the main context — a scenario recipe plus an implementation contract — then run Skill(scenario) followed by Skill(implement) and report JSON status. Make no design decisions and do not expand scope. Invoked exclusively by…

ondrej-merkun/skill-audit

Agent

This file tells Ralph (and any future contributor) how to build, test, and structure code in this repo. Keep it short and keep it accurate.

ondrej-merkun/skill-audit

Agent

Review the current implementation.

ondrej-merkun/skill-audit

Agent

Handle active cached agent work.

gw0/docker-claude-code

Agent

Web research and advisory agent for external knowledge gathering.

Mikacr1138/claude-bug-bounty

Agent

Subdomain enumeration and live host discovery specialist. Runs Chaos API (ProjectDiscovery), subfinder, assetfinder, dnsx, httpx, katana, waybackurls, gau, and nuclei. Produces prioritized attack surface for a target. Use when starting recon on a new target domain.

Mikacr1138/claude-bug-bounty

Agent

Bug bounty report writer. Generates professional H1/Bugcrowd/Intigriti/Immunefi reports. Impact-first writing, human tone, no theoretical language, CVSS 3.1 calculation included. Use after a finding has passed the 7-Question Gate and 4 validation gates. Never generates reports with "could potentially" language.

Mikacr1138/claude-bug-bounty

Agent

Smart contract security auditor. Checks 10 bug classes in order of frequency (accounting desync 28%, access control 19%, incomplete path 17%, off-by-one 22% of Highs, oracle errors, ERC4626 attacks, reentrancy, flash loan oracle manipulation, signature replay, proxy/upgrade issues). Applies pre-dive kill signals…

friedbotstudio/baseline

Agent

Agent "{{NAME}}" from friedbotstudio/baseline, covering operating envelope, inputs (provided by the caller), method (mandatory sequence) and constitutional constraints (binding — art. ii).

cosai-oasis/secure-ai-tooling

Agent

Version: 0.1.0-draft Scope: Authoring-time drafting of CoSAI Risk Map controls (secure-ai-tooling repository), pre-PR. Decision of record: ADR-031 (authoring-time agents and skills).

cosai-oasis/secure-ai-tooling

Agent

Version: 0.1.0-draft Scope: Pre-PR adversarial critique of CoSAI Risk Map control drafts (secure-ai-tooling repository). Decision of record: ADR-031 (authoring-time agents and skills).

cosai-oasis/secure-ai-tooling

Agent

Version: 0.1.0-draft Scope: Authoring-time drafting of CoSAI Risk Map risks (secure-ai-tooling repository), pre-PR. Decision of record: ADR-031 (authoring-time agents and skills); ADR-019 (risks schema).

cosai-oasis/secure-ai-tooling

Agent

Version: 0.1.0-draft Scope: Pre-PR adversarial critique of CoSAI Risk Map risk drafts (secure-ai-tooling repository). Decision of record: ADR-031 (authoring-time agents and skills); ADR-019 (risks schema).