一键导入
secrets-hygiene
Audits which skills have access to secrets, flags stale or unrotated credentials, and prompts rotation. Use weekly to keep credentials clean.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Audits which skills have access to secrets, flags stale or unrotated credentials, and prompts rotation. Use weekly to keep credentials clean.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | secrets-hygiene |
| description | Audits which skills have access to secrets, flags stale or unrotated credentials, and prompts rotation. Use weekly to keep credentials clean. |
| cron | 0 9 * * 1 |
| stateful | true |
State file: ~/.openclaw/skill-state/secrets-hygiene/state.yaml
Credentials you forgot about are credentials that will leak.
List all secrets currently configured in OpenClaw (env vars, config files, keychain entries referenced by installed skills). For each, record: name, which skills access it, when it was last rotated (if known).
A secret is stale if:
Send a summary:
Secrets Audit — [date]
[N] secrets tracked
[N] flagged for rotation: [names]
[N] orphaned (skill removed): [names]
Action needed: [yes/no]
Write last_audit_at, updated tracked_secrets list, flagged_count, orphaned_count to state file.
On Monday 9am wakeup:
last_audit_at is within the last 6 days, skipHandles PR review feedback by fetching comments, grouping issues, fixing one group at a time, and verifying before replies.
Reviews whether a skill will trigger reliably, guide useful behavior, avoid overlap, and produce testable outcomes.
Diagnoses OpenClaw provider, fallback, channel, MCP, and gateway config issues with read-only scans and stateful summaries.
Tracks required validation gates, records pass/fail/waived results, and reports readiness before task completion.
YAML-based delegation grant ledger — issues, validates, and tracks scoped permission grants for sub-agent expansions with token budgets and auto-expiry.
Walks the memory DAG to recall detailed context on demand — query, expand, and assemble cited answers from hierarchical summaries without re-reading raw transcripts.