Security & Testing Agent Skills for OpenAI Agents SDK

Guides the agent on executing static security scanning, auditing code for shell injections, and verifying API credential masks.

Stay strictly inside the current working directory — do not read, search, list, navigate to, or take any inspiration from anywhere else on…

Apply test-driven development with small, behavior-focused feedback loops.

Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check…

Strict RED->GREEN->REFACTOR test-driven development with enforcement.

Use when delegated work needs runtime guardrails — constrain sub-agents with loop detection, circuit breakers, and escalating sandbox…

Suede Labs AI eval design and coverage audit: AI-SPEC, failure-mode rubric with severity scoring, concrete pass/fail eval cases, coverage…

Suede Labs AI blunt A-F ship grade for a code change across correctness, security and permissions, data and state, domain truth, UX and…

Suede Labs AI MCP release QA, scoped to this pack's own server (mcp/suede-skills-mcp.mjs) and its catalog, install, and docs surface.

Create forensically sound bit-for-bit disk images using dd and dcfldd

Detect dangerous ACL misconfigurations in Active Directory using ldap3

Perform static analysis of Android APK malware samples using apktool

Parses API Gateway access logs (AWS API Gateway, Kong, Nginx) to detect

Analyze advanced persistent threat (APT) group techniques using MITRE

Queries Azure Monitor activity logs and sign-in logs via azure-monitor-query

Analyzes bootkit and advanced rootkit malware that infects the Master

Analyze Chromium-based browser artifacts using Hindsight to extract browsing

Campaign attribution analysis involves systematically evaluating evidence

Monitor Certificate Transparency logs using crt.sh and Certstream to

Detect abnormal access patterns in AWS S3, GCS, and Azure Blob Storage

Extract and analyze Cobalt Strike beacon configuration from PE files