trust-decay-monitor
andyxinweiminicloud 作
Git & GitHub概要
Helps track how AI skill verification results decay over time.
説明
このスキルでできること
Computes a trust freshness score for AI skills that carry security verification badges, tracking how much the original audit's conclusions have eroded over time. Factors in time since verification, dependency updates, new CVEs, and API endpoint changes. Produces a 0-100 score and re-verification urgency rating per skill.
Agent marketplaces display verification badges as permanent; this tool quantifies exactly how much trust has eroded since the original audit, turning a binary verified/unverified label into an actionable freshness score.
使いどころ
- Checking whether a 12-month-old verified skill badge still reflects current security
- Prioritizing which skills in a portfolio need re-auditing first
- Catching skills whose dependencies received major updates since their last audit
- Flagging skills that reference API endpoints that have since changed ownership or redirected
- Portfolio-level trust assessment before a production deployment
ワークフロー例
User asks: Check trust freshness for verified skill 'api-auth-helper' (verified 2025-01-10)
- 1
Retrieves verification date and original audit metadata for api-auth-helper
- 2
Calculates time-based decay: 408 days since audit yields -25 points
- 3
Checks dependency versions against audit baseline, finds 3 major updates to jsonwebtoken and related packages
- 4
Scans public CVE databases for JWT-related vulnerabilities published after the audit date
- 5
Verifies current API endpoint destination, detects redirect from v2 to v3 with a different response schema
Trust freshness score of 31/100 (STALE), decay breakdown by factor, re-verification urgency rated HIGH with specific drivers and recommended audit priorities
インストール
clawhub install andyxinweiminicloud/trust-decay-monitorCLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。