Skills

Converts product safety requirements into practical agent and LLM policies with abuse cases, escalation paths, safe defaults, audit events, and acceptance criteria.

Simulates realistic adversarial behavior against AI features to uncover prompt injection, data exfiltration, unsafe tool use, jailbreak, and authorization failures before launch.

Designs low-risk secret rotation for applications and agents, covering inventory, overlapping credentials, automation, audit evidence, emergency revocation, and rollback.

Reviews Model Context Protocol servers for excessive permissions, unsafe tool design, prompt injection exposure, secret handling, authorization gaps, and auditability.

Plans authorized penetration tests for systems you own or are permitted to assess. Defines scope, rules of engagement, and objectives; maps the attack surface; structures phases (recon, mapping, exploitation, post-exploitation, reporting) around a framework like the OWASP Testing Guide or PTES; and specifies safe handling of findings. Emphasizes explicit authorization and non-destructive testing.

Reviews applications and data flows for common privacy-regulation obligations (GDPR, CCPA/CPRA). Maps what personal data is collected, where it flows, and how long it is retained; checks for lawful basis, consent handling, data-subject rights, and third-party sharing; and produces a prioritized remediation list. Provides engineering guidance, not legal advice.

Reviews cloud IAM policies for least-privilege violations, overly broad wildcards, privilege escalation paths, and risky trust relationships across AWS, GCP, and Azure. Explains the risk of each finding and rewrites policies to grant only the permissions actually needed.

Red-teams LLM applications for prompt injection, jailbreaks, and data exfiltration risks. Generates adversarial test cases for direct and indirect injection, system prompt leakage, tool-call abuse, and unsafe output handling, then reports findings with severity ratings and concrete mitigations such as input isolation, output filtering, and least-privilege tools.

Performs systematic threat modeling for software systems using frameworks like STRIDE, PASTA, and Attack Trees. Identifies potential security threats, attack vectors, and vulnerabilities in system architectures. Produces prioritized risk assessments with mitigation strategies and security controls.

Security-first AI agent skill auditing. Reviews skill definitions, SKILL.md files, and agent configurations for dangerous patterns, excessive permissions, data exfiltration risks, and suspicious behaviors before installation. Provides a safety score and actionable recommendations.

Performs comprehensive security analysis of code and configurations. Identifies OWASP Top 10 vulnerabilities, insecure patterns, missing input validation, authentication flaws, and secrets exposure. Provides remediation steps with secure code examples.