Security & Testing Agent Skills for Perplexity

Verifies the authenticity and version of Claude models to detect proxies, wrappers, or downgraded AI versions.

Implement credit spending limits, data privacy enforcement, and input

Troubleshoot common Clerk errors and issues.

Implement user sign-up and sign-in flows with Clerk.

Handle user data, privacy, and GDPR compliance with Clerk.

Migrate from other authentication providers to Clerk.

Reference architecture patterns for Clerk authentication.

Common Clerk SDK patterns and best practices.

Inspect audit logs, manage access policies, view telemetry data, and review request history from the CLI.

Expert UX evaluator for CLIs, terminal tools, and developer APIs.

Trace every user-facing button/touchpoint through its full state change sequence to find bugs where functions individually work but cancel…

Run ClickHouse integration tests in CI with GitHub Actions and Docker containers.

The non-negotiable hard gates of a clinical EHR-automation workflow, each paired with the real incident that created it.

Harden containerized workloads against container-to-host escape and detect attempts.

Demonstrate cloud identity persistence during an authorized cloud assessment.

Demonstrate cloud credential theft via the instance metadata service (IMDS) during an authorized cloud assessment.

Harden cloud workloads against instance-metadata (IMDS) credential theft and detect attempts.

Demonstrate cloud audit-logging tampering during an authorized assessment — showing that an attacker with sufficient IAM can blind the…

Demonstrate container-to-host escape from an over-privileged container during an authorized assessment — privileged mode, host namespace…

Discover and prove publicly exposed cloud object storage during an authorized assessment — world-readable/writable S3 buckets, GCS…

Demonstrate serverless-function privilege escalation during an authorized cloud assessment — abusing an over-permissioned execution role…