hunt-llm-ai
De la autor
Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration via tool-use/markdown, ASCII smuggling, agentic AI security (OWASP Agentic Apps 2026, ASI01-ASI10). Patterns: direct injection ('ignore previous instructions'), indirect injection via documents/web pages/email the model reads, ASCII smuggling (Unicode Tags block U+E0000-U+E007F, invisible to humans, decoded by the model), tool-use exfiltration (model has fetch/browse tool, attacker injects OOB URL, model exfils chat history/secrets), markdown-image zero-click exfil, system-prompt extraction, IDOR-via-AI (cross-tenant data). Targets: chatbots, RAG, summarizers, agentic copilots, MCP tools. Detection: any LLM-backed endpoint, doc upload triggering AI processing, autonomous agent with tools. Validate: OOB/Collaborator callback for exfil, verbatim-reproducible system-prompt leak (run twice), verifiable cross-tenant leak or RCE. Confabulation is NOT a finding. Use when hunting AI features, chatbots, RAG, agentic systems, MCP.
Instalare
npx skills add elementalsouls/Claude-BugHunter --skill hunt-llm-ai -a claude-code
Se instalează în .claude/skills/hunt-llm-ai/ · Fiecare comandă descarcă skill-ul direct de pe GitHub cu utilitarul open source skills.
Fără descărcare: licența acestui skill (MIT) nu ne permite să-i redistribuim fișierele. Comenzile de instalare le iau direct de pe GitHub.
Vrei ca agentul să-ți propună skill-uri în timp ce scrii? Vezi cum folosești skill-urile din IDE.
Verificări de siguranță pe SKILL.md
- Îi cere agentului să-și ignore instrucțiunileRidicat
De ce 55
aiqbench calculează scorul de încredere din semnale publice. Nu este un audit de securitate, așa că citește un skill înainte să-l instalezi.
Skill-uri similare
Din aceeași categorie, cele mai de încredere primele. Acest skill nu este încă indexat pentru potrivire, așa că acestea sunt vecinii lui după categorie.
- ponytail-auditDietrichGebert/ponytailQuality audit of a whole repo: bugs, security holes, what breaks under real load, risky code without tests, slow paths, and what to delete, merge or split. Ranked, each finding explained in plain English. One-shot report, changes nothing. Use for "audit this codebase", "review the whole repo", "find bloat", "what can I delete", /ponytail-audit.Securitate★ 170.7K
- security-and-hardeningaddyosmani/agent-skillsHardens code against vulnerabilities. Use when auditing an input handler for vulnerabilities, when handling user input, authentication, data storage, or external integrations, or when checking a login flow is safe against the OWASP Top Ten. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services. Use when auditing dependencies for known vulnerabilities, triaging package-manager audit findings, or assessing supply-chain risk in a new package. Use when personal data or privacy compliance (GDPR, CCPA) is involved.Securitate★ 109.1K
- doubt-driven-developmentaddyosmani/agent-skillsSubjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production auth, security-sensitive logic, a high-stakes migration, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.Securitate★ 109.1K
- deal-with-security-advisorypaperclipai/paperclipHandle confidential GitHub Security Advisory response for Paperclip. Use when coordinating advisory triage, private-fork fixes, CVE/publication steps, and immediate security releases.Securitate★ 105.4K
- brandkitnexu-io/open-designPremium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.Securitate★ 102.9K
- setup-zoom-websocketsanthropics/knowledge-work-pluginsReference skill for Zoom WebSockets. Use after routing to a low-latency event workflow when persistent connections, faster event delivery, or security constraints make WebSockets preferable to webhooks.OficialSecuritate★ 31K
Note și recenzii
—
nicio recenzie
Ai încercat acest skill? Notează-l ca să-i ajuți pe alții. Autentifică-te
Discuție
Intră în discuție. Autentifică-te