dsh-secret-scrub
Irreversible secret-scrubbing guard: rewrites access keys, bearer tokens, and private key blocks into `[REDACTED:<category>]` placeholders before they reach the session log and the model.
不可逆密钥脱敏守护：在访问密钥、Bearer 令牌、私钥块进入会话日志和模型请求之前，将其改写为 `[REDACTED:<category>]` 占位符。
How to install
dsh plugin add dsh-secret-scrub About
dsh-secret-scrub English | 中文 Irreversible secret-scrubbing guard plugin, extracted from the user-sensitive-information protection strategy of the kaya-ai-terminal project and open-sourced standalone (Mainland China site: https://www.yunhouai.com; international site: https://www.yunhou.ai). It rewrites text on its way to the session log and the model: when a configured rule matches a secret-shaped fragment — an access key, a bearer token, a private key block — the fragment is replaced irreversibly with a [REDACTED:<category>] placeholder, so the durable log and the model request carry only the…
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 1
- mo. downloads
- –
- Last push
- 2026-09-02
- Created
- 2026-09-02
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin, curated:0xsline/awesome-deepseek-harness
- Topics
- cordis, deepseek-harness, dsh, dsh-plugin, llm-security, privacy, redaction, secret-scanning
Related plugins
sofagent
KongFangXun/sofagent/tree/main/engine/dsh-plugins/cordis-plugin-sofagent-audit
Commit-time audit harness for AI coding agents: 24 git-diff rules (secrets, out-of-scope edits, prompt injection), HMAC-signed audit trail, snapshot rollback, and an MCP server with 79 tools. Installable via dsh plugin add.
dsh-web-startup-auth
GDWhisper/dsh-web-startup-auth
Replaces the dsh web startup to allow binding 0.0.0.0, gated by username/password login: signed session cookies, /api route protection, an auth tab in the settings panel, and a reset CLI that rotates the signing key to invalidate all sessions.
dsh-auto-approve
Jiao-XXX/dsh-auto-approve
Adds an `auto` permission preset between workspace-write and danger-full-access: a classifier grants routine sandbox escalations once, while dangerous or uncertain requests still go to a human.
dsh-auto-review
PerryLink/dsh-auto-review
Second-model auto-review on the approval answerer chain: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default.