91 results
Zero-dependency static + sandbox smoke detector for DeepSeek Harness (dsh) plugins: package-structure gates (R), cordis contract scans (K), keyless-headless sandbox smoke (D), and ecosystem-listing checks (CC).
DeepSeek Harness plugin: redacts known secret shapes in tool arguments and results behind stable placeholders, and appends preimage-free JSONL incidents
DSH compatibility guard: repairs compaction limits, fail-safe sandbox escalation, and missing tool descriptions for third-party models; capability lookups are cached and the deprecated prompt-injection path is off by default.
Make a Git for Windows installation resolvable as `bash` inside the dsh host process, so the official bash shell stack (dsh-bash-sandbox + dsh-tool-bash) can run on Windows
Strict check: verify code and commands against real checkers instead of reading them — Lean 4 kernel checking with an axiom audit, language type/syntax checks, and static defect rules.
Declarative Claude Code-style permission rules plus a Codex-style process-level network policy for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), workspace-path, and network-target (domain/ip/port/scheme) matching on
Config drift detective for DSH: snapshots profile/plugin state on startup, records diffs, exposes a read-only history tool. Zero runtime deps, no custom events.
Zero-interruption audit + fuse blocking for DeepSeek Harness. / 零打扰 Agent 审计与保险丝拦截插件。
Evidence-backed runtime nutrition labels for DeepSeek Harness plugins and tool namespaces
Installation safety gate & data-protection guard for DeepSeek Harness: 60 static signature rules scan plugin sources for malicious install scripts, credential theft, obfuscation and network callbacks before 'dsh plugin add', with scan baselines (gate_diff), structured reports (gate_report), 12 destructive-command patterns and workspace-boundary checks.
Runtime data-flow audit log for DeepSeek Harness: who mutated what, in what order — per-plugin, per-fiber attribution.
Local tool-call failsafe and DWGR-8 personal governance proxy gate for DSH: blocks high-risk shell patterns, credential leaks, and enforces declarative param-level boundaries with hash-linked JSONL audit logs and optional Gateway.
Static linter: every plugin HTTP route must carry a browser-trust fence (loopback Host pin before Origin / sec-fetch-site).
Read-only security & compliance toolkit for DeepSeek Harness: prompt-injection detection (rule engine with a pluggable model classifier), Chinese-PII redaction, and a local configuration security audit that emits redacted, reproducible risk reports.
Indirect prompt-injection guard for DeepSeek Harness: taints tool output by origin and gates privileged tool calls that follow untrusted content
AI-reviewed auto-approval for DeepSeek Harness: judges each pending approval ask with one auxiliary model call before any human answerer runs, auto-grants the safe ones, and escalates everything else with the review analysis attached
Run an agent unattended for hours and get a morning brief that is an audit, not a summary. Signs a manifest before the work, holds the run to it, and reports the difference.
Deny an AI agent access to .env files, credential stores, keys and any path you hide — across file tools, shell commands, search selectors and run_code. A DeepSeek Harness (dsh) plugin.
Allowlisted git execution for DeepSeek Harness: a model-facing git tool that runs outside the file sandbox, with a settings page where the user ticks which git subcommands are permitted and, per path, which reads and writes are allowed, prompted or refused