Draft evidence-backed answers to vendor security questionnaires and RFP security sections — no invented compliance claims.
I specialize in safe Codex skill onboarding. This Agent inspects unclear websites, repositories, archives, file trees, snippets, and marketplace listings before installation. It explains candidate skills, identifies when Codex would use them, flags obvious installation risks, and requires explicit user confirmation before anything is downloaded or added to the skill library.
Upload a security questionnaire, add company documents, or paste a product URL. Get evidence-linked draft answers and grouped follow-ups for your team. Add new information to update only the affected answers. Missing facts and conflicting sources are clearly flagged for review.
Audit AI agents, Skills, MCP configurations, tool permissions, and coding-agent setups for prompt injection, excessive agency, credential exposure, data leakage, unsafe code execution, supply-chain risks, memory risks, missing approval controls, and runaway autonomy. Get a calibrated Security Score, Audit Confidence, evidence-backed findings, remediation steps, verification checks, and residual-risk analysis.
從「業務戰力診斷」到個人拓客作戰包——一條 SOP 跑完競品分析、準客戶痛點、個人定位、在地SEO、廣告文案、短影音腳本，全部對 齊同一突破口，並過行業合規（房仲／保險／車商）。適合想擺脫只靠公司派單、要建立個人品牌與穩定名單的業務員。
看懂退休現金流，不只要看配息，更要理解通膨、市場波動、流動性、提領時點與序列報酬風險。 IncomeFlow AI 協助你理解成長型、現金流型與防守型資產的功能與限制、DRIP 紅利再投資，以及尋求專業財務顧問前應先釐清的重點。 專注於理財教育與風險辨識，不提供特定金融商品分析或推薦、個人化配置比例、金額試算或買賣建議。
Forces AI agents to anchor every interview answer in verified company facts, mark all personal examples as [USER_INPUT_REQUIRED] until you provide them, and label every unsourced claim — so nothing fabricated makes it into your next interview.
Review an AI Skill before installation or publication. Get a concrete verdict with evidence, permissions, secret risks, license constraints, and the safest next step.
This Skill is built on practical expertise in AI agent safety, prompt-injection defense, source-to-sink privacy review, tool and MCP metadata integrity, memory provenance checks, autonomous action scoping, and evidence-based verification. It helps agents separate instructions from evidence before tool calls, uploads, publishing, deletion, code execution, or network output.