Security & Testing Agent Skills for Gemini CLI

Audit a port for everything that did NOT make it across — features, screens, commands, peripherals, protocol fields, config keys, assets…

Implement Mistral AI PII handling, data retention, and GDPR/CCPA compliance

Apply Mistral AI security best practices for secrets, prompt injection,

Systematically finds and fixes bugs using proven debugging techniques.

MITRE ATT&CK framework mapping and analysis

Abuse the trust a backend places in its mobile client during an authorized assessment.

Demonstrate Insufficient Binary Protections (OWASP Mobile Top 10 M7) during an authorized mobile assessment — bypassing an app's…

Use cryptography correctly in a mobile app against OWASP Mobile Top 10 M10.

Recover sensitive data a mobile app leaves on the device during an authorized mobile assessment.

Demonstrate Inadequate Privacy Controls (OWASP Mobile Top 10 M6) during an authorized mobile assessment — showing that an app collects…

Mobile application security skill for implementing OWASP MASVS compliance, secure storage, certificate pinning, biometric authentication…

Demonstrate Security Misconfiguration (OWASP Mobile Top 10 M8) during an authorized mobile assessment — finding insecure platform and app…

Audit a live web page in five phases (catalog, click, trace, classify, report) to identify mock data, hardcoded values, LLM-generated…

Create tests following Vitest and Playwright patterns.

Use when implementing any feature or bugfix, before writing implementation code

When it comes to money laundering: negotiation, settlement and escalation in money laundering prevention, AML and KYC: develops a…

Monitors dark web forums, marketplaces, paste sites, and ransomware

Hunt NTLM/Negotiate information disclosure on internet-reachable IIS/SharePoint/Exchange.

Mock Service Worker API mocking, request handlers, and integration testing.

Run Stryker mutation testing on the source files changed in the current branch (vs origin/master) across vitest packages.

Run Stryker mutation testing on a single source file and return a structured, token-frugal report that's pipeable to a follow-up…