Detects prompt-injection, jailbreak, and secret-leak patterns on the agent/pre-step, tools/pre-execute, and tools/post-execute seams with allow/ask/block tiers, sanitized defend/detection audit events, a defend_report tool, and a destructive-delete command guard.
Install
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:PerryLink/dsh-defend
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).
Links
More in this category
toby-bridges/api-relay-audit★ 799
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★ 201
Authorized pentest mode for DeepSeek Harness — exploration chain, assets and findings with a Web view.
PerryLink/dsh-auto-review★ 80
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.
xgone/dsh-remote★ 42
Remote access & authentication for DeepSeek Harness web UI: account/password login gate, MFA (TOTP), signed session cookies, role-based access, in-browser directory picker, account management settings, fully localized in English and Chinese.
PerryLink/dsh-permission-rules★ 29
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★ 18
Read-only security and compliance plugin for DeepSeek Harness: prompt-injection detection, Chinese-PII redaction, and a local configuration audit with redacted, reproducible reports.