Security & Testing Agent Skills for Cursor

Enables ultra-granular, line-by-line code analysis to build deep architectural context before vulnerability or bug finding.

Enables ultra-granular, line-by-line code analysis to build deep architectural context before vulnerability or bug finding.

Enforces strict pre-delivery self-inspection, disk re-reading, and encoding verification to eliminate AI hallucinations and low-level file…

Implement audio data handling best practices for Deepgram integrations.

Performs in-depth security audits and vulnerability assessments to protect codebases from exploits and insecure patterns.

End-to-end smoke test skill for DeerFlow.

Use when invalid data causes failures deep in execution, requiring validation at multiple system layers - validates at every layer data…

Perform authorized defensive correctness reviews of the user's own local software repositories.

Audits project dependencies for security vulnerabilities, license compliance issues, outdated packages, and transitive dependency risk.

Software Composition Analysis (SCA) and dependency vulnerability scanning.

Scan package manifests and lockfiles for outdated and vulnerable dependencies.

Master major dependency version upgrades, compatibility analysis, staged upgrade strategies, and comprehensive testing approaches.

Deploy cloud-native deception across AWS, Azure, and GCP using decoy (honey) resources whose only purpose is to generate a high-fidelity…

Resolve a deployment_id into the artifacts that make up one agentic deployment and build the evidence graph every other attestation skill…

Plan, run, and measure an adversary engagement operation using the MITRE Engage framework so that deployed deception is driven by strategy…

Writes and tunes Falco rule syntax for container escape detection - conditions, macros, lists, priorities, and output fields - covering…

Write and deploy Falco rules with the modern eBPF driver to detect container escape, namespace abuse, privileged mounts, and anomalous…

This skill teaches security teams how to detect and respond to unauthorized

Identify poisoned training data and backdoored models across the ML pipeline.

Detect DCSync attacks (MITRE T1003.006) where adversaries abuse Active Directory replication privileges to extract password hashes, by…

Detect data exfiltration via DNS tunneling (tools like iodine, dnscat2, dns2tcp) by analyzing query entropy, subdomain length, query…