Manual approval mode ("Manual Mode" / "Ask Mode").
Install
# from npm (prebuilt)
dsh plugin --profile web add dsh-tool-approval
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:ilharp/dsh-tool-approval
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
English | 中文
Add pre-approval to any Tool Calling, aka "Manual Mode"/"Ask Mode".
Install
dsh plugin --profile web add dsh-tool-approval
Config
Default config
- id: tool-approval
name: dsh-tool-approval
With the default config, every Tool Calling goes through pre-approval.
Custom config
- id: tool-approval
name: dsh-tool-approval
config:
include: [fs_*, web_*]
exclude: [task_output]
reason: tool execution requires your approval
Only tools specified in include get pre-approval; tools in exclude pass through. Wildcards are supported.
LICENSE
Links
More in this category
toby-bridges/api-relay-audit★ 819
Runs local security audits of AI API relays and LLM proxies from DeepSeek Harness, producing Markdown reports for prompt injection, model substitution signals, tool-call rewriting, error leakage, stream integrity, and profile-gated Web3 risks.
howmp/dsh-pentest★ 330
Authorized pentest mode for DeepSeek Harness — exploration chain, assets and findings with a Web view.
SeaOf0/dsh-redteam-model★ 138
Authorized-security DSH collection: nine work modes (redteam coordinator, pentest, code audit, binary analysis, attack-defense, AV evasion, incident response, cloud security, CTF solving) and fifteen runtime plugins, managed from a settings page with one-click deploy, install, update and uninstall.
PerryLink/dsh-auto-review★ 124
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.
PerryLink/dsh-permission-rules★ 81
Claude Code-style declarative permission rules: ordered allow/deny/ask YAML rules matching tool names, arguments, workspace paths, and agent identity on the tools/pre-execute waterfall, with full session-log audit, dry-run mode, and hot reload.
PensiveFei/dsh-secure-audit★ 72
Read-only security and compliance plugin for DeepSeek Harness: prompt-injection detection, Chinese-PII redaction, and a local configuration audit with redacted, reproducible reports.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.