Review AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review. Use when asked whether a skill or downloaded skill folder is safe, trustworthy, installable, over-permissioned, or malicious.
GraphQL security hunting — introspection abuse, field suggestion enumeration (clairvoyance), batching DoS, IDOR via aliasing, auth bypass, injection via arguments, subscription abuse, depth/complexity bombs, and WAF bypass. Covers graphw00f fingerprinting, gqlmap, graphql-cop, and inql. Use when a target exposes a…
Bugcrowd-specific reporting tactics complementing report-writing: VRT category search-and-fallback strategy when no exact match exists, manual severity override when VRT defaults underrate impact, severity-request paragraph as first body section, OOS-clause rebuttal templates (rate limiting on auth-flow endpoints…
Finds flaky tests on the main branch by analyzing GitHub Actions failures, ranks them by frequency, and enters parallel plan mode to design deflake strategies. Use when you want to find and fix the flakiest tests.
Generates polished GitHub release notes for a ToolHive release by analyzing every merged PR, cross-referencing linked issues, dispatching expert agents to assess breaking changes, and producing a formatted release body. Use when the user provides a GitHub release URL, tag name, or says "release notes".
Guide for using ToolHive CLI (thv) to run and manage MCP servers and skills. Use when running, listing, stopping, building, or configuring MCP servers locally. Covers server lifecycle, registry browsing, secrets management, client registration, groups, container builds, exports, permissions, network isolation…
Detect insecure file upload vulnerabilities in a codebase using a three-phase approach: discovery (find all upload sites), batched verify (check extension bypass and related issues in parallel subagents, 3 sites each), and merge (consolidate batch results). Requires sast/architecture.md (run sast-analysis first).…
Detect path traversal vulnerabilities in a codebase using a three-phase approach: recon (find file-loading sinks with dynamic paths), batched verify (trace user input and mitigations in parallel subagents, 3 sinks each), and merge (consolidate batch results). Requires sast/architecture.md (run sast-analysis first).…
Detect Server-Side Template Injection (SSTI) vulnerabilities in a codebase using a three-phase approach: recon (find template rendering sites that use dynamic strings), batched verify (trace user input to those sites in parallel subagents, 3 candidates each), and merge (consolidate batch results). Requires…
Turn a MITRE ATT&CK/ATLAS threat group or case study — or a frontier AI agent deployed inside the organisation — into a full incident-response tabletop exercise (MSEL): scenario narrative, kill chain or agent threat scope, timestamped injects, discussion questions, and a detection-coverage scorecard, using the…
Use when connecting Codex, Claude Code, OpenCode, OpenClaw, coding-agent CLIs, agent gateways, workspaces, sandbox policies, provider files, or trace capture to Promptbeat as an evaluation target.
Use when a user wants to start using a downloaded Promptbeat full package, connect an HTTP agent, LLM, coding agent, choose an evaluation path, run a first red-team test, or asks where to begin.
Use when a user needs help choosing Promptbeat attack goals, risk types, scenarios, seed files, dataset subscriptions, compliance profiles, or a small smoke-test scope.