skill-update-delta-monitor
от andyxinweiminicloud
Git & GitHubКратко
Helps detect security-relevant changes in AI skills after installation.
Описание
Что делает этот навык
Monitors AI skills for security-relevant changes introduced after installation. Tracks permission scope, new network endpoints, dependency chain updates, and instruction drift between the audited version and the current one. Produces a risk classification of CLEAN, WATCH, REVIEW, or ROLLBACK.
Install-time audits are point-in-time snapshots, so this catches the class of post-install updates that introduce malicious behavior after the verification window has closed.
Когда его использовать
- Checking if a trusted skill quietly added outbound network calls
- Auditing a skill that released multiple updates in a short window
- Reviewing permission expansions after a dependency major version bump
- Comparing installed vs current skill before running it on sensitive data
- Generating rollback guidance when a skill's instruction framing shifts
Пример сценария
User asks: Has the data-formatter skill changed since I installed version 1.2.0?
- 1
Accept skill identifier and audited baseline version as input
- 2
Fetch current version metadata and diff permission declarations across all intermediate versions
- 3
Detect new outbound network endpoints and changed dependency chains
- 4
Score instruction drift by comparing SKILL.md natural language across versions
- 5
Classify overall risk and identify the audited baseline as a rollback target
Delta report with permission scope diff, new endpoints, dependency changes, instruction drift score, version velocity assessment, and risk classification REVIEW with rollback option to v1.2.0
Установка
clawhub install andyxinweiminicloud/skill-update-delta-monitorВыполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.