Agent Skills: gemini-cli-security
AI-powered code vulnerability analysis and dependency scanning using Gemini CLI security extension patterns. Detects hardcoded secrets, injection attacks, weak cryptography, authentication flaws, and LLM prompt injection. Also scans dependencies against the OSV.dev vulnerability database.
ID: oimiragieo/agent-studio/gemini-cli-security
416
Install this agent skill to your local
Skill Files
The files that make up gemini-cli-security.
More agent skills
- chrome-devtoolsBrowser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.
- backend-patternsBackend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes. Use when building or reviewing Node.js, Express, or Next.js API routes and their data access.
- frontend-architectureHow to organize frontend code — separation of concerns (UI / logic / data / type), file responsibility, state tiers, API services, schema validation, and framework conventions for React/Next and Vue. Structural rules, not visual design.
- monitor-servicesCheck the active Pollinations GPU backends and recover a confirmed failure of an existing worker when the task authorizes repair. Use for recurring health checks and GPU incidents; use manage-vast-gpu-fleet for replacements.
- snowflake-semantic-viewsCreate, alter, validate, audit, debug, and optimize Snowflake semantic views using Snowflake CLI (`snow`), SQL DDL, YAML semantic view specs, Cortex Analyst verified queries, and Snowflake validation procedures. Use when asked to build semantic views, troubleshoot CREATE/ALTER SEMANTIC VIEW or SYSTEM$CREATE_SEMANTIC_VIEW_FROM_YAML failures, enrich comments/synonyms/metrics/filters/relationships, add or validate AI_VERIFIED_QUERIES, or test semantic views against Snowflake.
- creating-modsCreates and edits trusted local Letta Code mods, including tools, slash commands, local-only model providers, lifecycle/turn events, scoped conversation helpers, panels, and capability-gated behavior. Use when asked to make a mod, add an agent-callable tool, add a slash command, add a local provider/model adapter, transform turns, react to app events, or add lightweight mod UI outside the dedicated /statusline flow.