privesc-linux-vectors

Use when testing a web application for SQL injection on an authorized engagement.

7 skills

Use when planning or running nmap scans during authorized engagements: host discovery options, TCP SYN, connect, UDP, NULL, FIN, Xmas, and ACK scan types, service and OS detection, timing templates T0 to T5, evasion techniques (fragmentation, decoys, idle scans, source port tricks, data length padding), NSE script selection by category, and output formats for evidence.

6 skills

Use when you hold a low-privilege Linux shell on an authorized engagement, lab, or CTF and need a reliable path to root.

6 skills

Use when testing a web application for cross-site scripting on an authorized engagement.

6 skills

Use when mapping an authorized Active Directory environment during an internal assessment or assumed breach exercise.

5 skills

Use when testing REST, GraphQL, or internal APIs on an authorized engagement.

5 skills

AgentDB (external: maintained in ruvnet/agentdb, pinned to commit 27678c3, plugin 3.6.0): agentdb's own standalone MCP server pinned to [email protected] (vector memory with get/list/update/delete for records, patterns and skills, hybrid keyword + vector episode search and an opt-in local cross-encoder, an opt-in aidefence injection guard on memory writes, reflexion, skills, outcome feedback, capabilities report), a memory-specialist agent, 3 skills, /agentdb-status, and the agentdb mod guard that keeps secrets out of memory and refuses delete/reset unless allowed. Complements ruflo-agentdb, which reaches AgentDB through ruflo's server

3 skills · 1 command · 1 agent · 1 MCP server

Harness Adobe's creative AI-powered tools to edit images, automate design workflows, and bring creative visions to life — from background removal to vectorization and professional retouching.

26 skills · 1 MCP server

LLM application development with LangGraph, RAG systems, vector search, and AI agent architectures for Claude 4.6 and GPT-5.4

8 skills · 3 commands · 3 agents

Agent skills for Qdrant vector search: scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage

33 skills

Comprehensive C/C++ security code review, with coverage verified against a parse of the source

1 skill · 1 agent

Hooks that send each Claude Code tool call to a local Tracekit signer before it runs: allowed, denied with the rule that matched, or held until you approve it from another terminal. The signer signs every call, decision and result into a hash-chained record that `tracekit verify` checks offline. Needs the tracekit-ai Python package (`pip install tracekit-ai==1.6.0 && tracekit init --dev --v2 --no-hooks`). In that dev mode the signer runs as your own user; on Linux, system mode runs it as a separate user.

3 skills · 3 commands · hooks