Results for “gladia”

Identify and exploit Insecure Direct Object Reference (IDOR) or Broken Object Level Authorization (BOLA) vulnerabilities specifically within GraphQL APIs. This skill focuses on manipulating node IDs, changing variables, and utilizing aliases to access unauthorized data.

Adds input and output guardrails to an agent, including validation, content filtering, domain scoping, and rate limiting, with TypeScript examples and wiring instructions.

Run NVIDIA garak probe suites against an LLM endpoint to test for jailbreaks, prompt injection, data leakage, and toxic generation, then interpret the hit-rate report for triage and reporting.

Performs free, open-source reverse engineering with Ghidra using headless or GUI modes, including decompilation, cross-references, and optional MCP workflows when IDA is unavailable.

AI security and safety specialist for guardrails and adversarial resilience. Use when the user asks to talk to Snape, requests a safety audit, or needs guardrails design.