dsh-approve-for-me
Rule-gated automatic sandbox escalation approval with optional LLM review and native human fallback for DeepSeek Harness.
Install
$ dsh plugin --profile web add dsh-approve-for-me@latestPlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Applies strict fixed high-risk checks and literal command prefix rules for Shell and PowerShell commands
- Supports optional tool-free LLM review using the requesting session's model configuration
- Issues single-use (allowed-once) grants instead of permanent sandbox escalations
- Falls back to Harness native human approval for ambiguous, unlisted, or high-risk commands
- Provides an optional Web UI settings card via the keyed third-party settings slot for loopback connections
- Integrates with Harness Profile-specific settings and YAML configurations without exposing stored credentials
Useful For
- Automating routine, safe developer commands (e.g., git status, git diff) during DeepSeek Harness agent sessions
- Enforcing policy boundaries on command execution without completely disabling sandbox safety
- Headless automation pipelines where pre-approved read-only shell commands run unattended while unlisted commands pause for review
Who It Fits
- Developers looking to reduce repetitive manual escalation prompts in DeepSeek Harness
- Security-conscious teams needing customizable command allowlists and fallback policies for agent sandboxes
- Automated or headless agent operators requiring safe one-time escalation approvals
Documented Limitations
- Empty allowlist by default; requires explicit configuration of allowed command prefixes to take effect
- Built-in risk checks do not guarantee complete safety against all dynamic or wrapped commands
- Web configuration card is accessible only over loopback connections (e.g., 127.0.0.1)
- Compound commands require every single segment to pass rule validation independently
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 1 runtime, 28 development, 18 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- timeance/dsh-approve-for-me
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 95a7d93 · 2026-08-28
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 11GitHub stars
- Forks
- 1
- Open issues
- 0
- Last commit
- 2026-08-28
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Second-model approval reviewer for DeepSeek Harness that returns structured allow/deny verdicts with fail-closed fallback and session-log auditing.
View plugin →Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →Governance-powered AI-agent task execution framework with a DeepSeek Harness plugin integration.
View plugin →Sandbox-first automatic permission policy and intelligent risk classification for DeepSeek Harness.
View plugin →