dsh-dros-vajraclaw
Local tool-call failsafe and execution governance plugin blocking high-risk shell commands and credential leaks with audit logging.
Install
$ dsh plugin --profile web add dsh-plugin-vajraclawPlugin 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
- Embedded local regex failsafe blocking high-risk shell execution patterns and destructive commands
- Sensitive file path and credential read protection (.env, id_rsa, cloud credentials)
- Persistent hash-linked JSONL audit trail tracking tool-call execution history across sessions
- Configurable security boundaries via plain Markdown (Vajra.md) or YAML policies
- Optional integration with external DROS Gateway for multi-agent policy orchestration and RFC-010 W3C DID cryptographic verification
Useful For
- Preventing autonomous agent hallucinations from executing destructive filesystem or system-level terminal commands
- Securing local developer environments against indirect prompt injection attempting credential exfiltration
- Maintaining an auditable, tamper-evident record of all tool calls executed within DSH workflows
- Connecting DSH sessions to a unified multi-agent governance perimeter alongside other AI workstations
Who It Fits
- Developers deploying autonomous DSH agents with terminal and filesystem tool capabilities
- Security engineers requiring local execution circuit breakers and fail-closed runtime policies
- Multi-agent workstation operators needing unified security guardrails and audit logging
Documented Limitations
- Embedded mode is restricted to local regex pattern matching and path heuristics within DSH
- Advanced cryptographic identity features (W3C DID, AST bitmap matrix) require running the external DROS Gateway Docker container
- Commercial deployments require purchasing an enterprise license key
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.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- Top-Celestial-Company-Ltd/dsh-dros-vajraclaw
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 3360e7a · 2026-09-05
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
- 0GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-09-05
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Sandbox-first automatic permission policy and intelligent risk classification for DeepSeek Harness.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed safety and session audit.
View plugin →Composable three-tier memory control plane for DeepSeek Harness with runtime context, searchable documents, and pluggable long-term memory.
View plugin →Native SQLite-backed local project taskboard plugin and UI for DeepSeek Harness with Agent claim and review flows.
View plugin →