154 tagged Prompt Injection, measured the same way as everything else here.
Browse within: ai-security 59openclaw 45devsecops 42code-scanning 30llm-security 28prompt-engineering 22agent-design 15cangjie-skill 15context-management 15ai-red-teaming 10公众号 10owasp 8jailbreak 7kubernetes 7
Skill Claude CodeCodex
Run one iteration of the autoresearch loop — study existing attack methods, design a better optimizer, implement it, benchmark it, and commit. Meant to be called repeatedly via /loop.
kangarooking/system-prompt-skills
Skill Claude CodeCodex
A guide for designing systems where several specialised AI agents share work. It covers dividing responsibilities, passing short task summaries, managing task stages, and checking results.
kangarooking/system-prompt-skills
Skill Claude CodeCodex
Design guidance for giving an AI a persistent memory system. It covers storing, finding, using, changing, and deleting information such as user preferences and project knowledge.
kangarooking/system-prompt-skills
Skill Claude CodeCodex
Tool specification defines how an AI discovers, describes, authorizes, and uses external tools. Tools are connected functions or services, such as APIs, browsers, or file operations.
Skill Claude CodeCodex
600+ pattern AI agent security defense covering prompt injection, supply chain injection, memory poisoning, action gate bypass, unicode steganography, and cascade amplification. Optional API for early-access and premium patterns. Tiered loading, hash cache, 11 SHIELD categories, 10 languages.
CyberStrategyInstitute/ai-safe2-framework
Skill Claude CodeCodex
Apply AI SAFE2 v3.1 to design, build, audit, test, and govern AI agents, multi-agent systems, RAG, MCP/tool integrations, and AI infrastructure. Use the 161-control core taxonomy plus applicable profile overlays such as CP.5.MCP MCP-1 through MCP-19. Classify autonomy with ACT tiers, enforce HEAR and replication…
Skill Claude CodeCodex
A security deployment guide for OpenClaw, with instructions in English and Chinese. It covers network exposure, container isolation, credentials, permissions, and audit logging.
samarailly51-pixel/claimpilot-harness
Skill Claude CodeCodex
Review and structure auto insurance bodily injury claims, including intake triage, evidence completeness, injury causation, treatment chronology, medical necessity, wage-loss support, negotiation risks, and human escalation. Use when analyzing bodily injury claim files, designing claims-agent workflows, drafting…
Skill Claude CodeCodex
Scan packages, repositories, MCP servers, domains, web pages, and agent skills for security threats using the brin API. Use this skill before installing dependencies, visiting URLs, or integrating external resources.
Skill Claude CodeCodex
Part of sentinel-ai
Automatically scan user inputs and LLM outputs for safety issues including prompt injection, PII leaks, harmful content, toxicity, and hallucinations. Use when processing untrusted text, reviewing code for security issues, or validating LLM responses.
Skill Claude CodeCodex
Use when the user asks to scan a repo for AI/LLM security issues, wants to know "is this skill safe?" before installing an Agent Skill, needs to "scan my MCP config" or check an MCP server before trusting it, asks about prompt injection / tool poisoning / RAG poisoning risk in their code, or is about to install any…
Skill Claude CodeCodex
Documents how to add a provider package to the SDK monorepo.
Skill Claude CodeCodex
Appends a note the user provides to the project's activity log.
EvolutionUnleashed/skill-sentinel
Skill Claude CodeCodex
Security scanner and threat analyzer for AI agent skills. Activate this skill whenever a new skill is added to the workspace, when the user imports or installs a skill from an external source, when asked to audit or review an existing skill for safety, or when the user mentions scanning, vetting, checking, or…
screem500/prompt-injection-auditor
Skill Claude CodeCodex
Security audit of LLM system prompts, agent instruction files (SKILL.md, AGENTS.md, CLAUDE.md), and agent configurations against prompt injection attacks. Use when the user wants to (1) audit or harden a system prompt or agent instructions against prompt injection, (2) review an agent skill or system prompt for…
Skill Claude CodeCodex
Audit supplied evidence for AI coding-agent extensions, Codex plugins, Claude Code extensions, and MCP servers using concrete supply-chain security indicators.
Skill Claude CodeCodex
Convert repositories, books, incident reports, transcripts, documentation, and other source material into the smallest justified AI skill or reference artifact. Use when extracting reusable practices from external or internal sources, deciding whether material deserves promotion into agent instructions, building an…
Skill Claude CodeCodex
Recurring security & correctness audit of the infrabroker repo. Iteratively find, fix, and CLOSE issues across security / logic / documentation — each finding tracked as a GitHub issue, each fix landing as an auto-merged PR that closes it. Use when the user asks to audit the repo, run a security/correctness pass, hunt…
Skill Claude CodeCodex
Work a GitHub issue of infrabroker end-to-end — branch first, implement with tests, changelog entry under [Unreleased], make verify, then a PR that closes the issue on merge (auto-merge). Use when the user asks to work on, implement, fix or ship a specific issue, pick up the next issue from the backlog, or continue…
Skill Claude CodeCodex
Cut and publish a new infrabroker release end-to-end — semver bump, CHANGELOG (folding the [Unreleased] section), server.json + HANDOFF, make verify, release PR, annotated tag, and the CI-driven GitHub release + multi-arch ghcr image + MCP Registry publish. Use when the user asks to release, publish, cut/ship/tag a…
Skill Claude CodeCodex
Part of polygraph
Behavioral trust grades (A–F) for MCP servers. Use when an agent needs to check whether an MCP server is safe before using it, verify an onchain attestation before trusting or paying a server, look up a server's published grade, get a project graded, or understand why a server received a grade. Polygraph connects to…
Skill Claude CodeCodex
Part of code-factory-langgraph
Use when building, reviewing, or debugging a LangGraph flow that must prove a resumed run preserved its recorded semantic transitions and side-effect discipline.
Skill Claude CodeCodex
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, debugging, testing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Skill Claude CodeCodex
Use when: the user asks to run system maintenance. Capability: executes shell commands via shellexec. Route maintenance commands through the system shell and run them.
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: