hunt-llm-ai
From the author
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.
Install
npx skills add elementalsouls/Claude-BugHunter --skill hunt-llm-ai -a claude-code
Installs to .claude/skills/hunt-llm-ai/ · Each command fetches the skill straight from GitHub with the open skills CLI.
No download: this skill’s licence (MIT) does not let us redistribute its files. The install commands fetch them from GitHub instead.
Want your agent to suggest skills while you type? See how to use skills from your IDE.
Safety checks on SKILL.md
- Tells the agent to ignore its instructionsHigh
Why 55
aiqbench computes the trust score from public signals. It is not a security audit, so read a skill before you install it.
Similar skills
From the same category, best-trusted first. This skill is not indexed for matching yet, so these are its neighbours by category.
- 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.Security★ 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.Security★ 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.Security★ 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.Security★ 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.Security★ 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.OfficialSecurity★ 31K
Ratings & reviews
—
no reviews
Tried this skill? Rate it to help others. Sign in
Discussion
Join the discussion. Sign in