DeepSeek Harness
DeepSeek Harness: Everything is a Plugin.
Is DeepSeek Harness safe? Promising trust profile, but some evidence still deserves review.
Compare DeepSeek Harness
How does it stack up against its Coding Agents neighbours?
Pick any agent to compare →In detail: DeepSeek Harness scores 72.6/100 (Grade B), ranked #280 of 1343 tracked open-source AI agent projects, on evidence coverage B (3 of 5 independent signal types). The public evidence: no package-provenance attestation found; OSSF Scorecard rates its supply-chain practices 4.6/10; recent commits are unsigned; no published advisory affects its latest release (@deepseek-ai/dsh); last pushed 2026-09-29. Every point is earned from checkable signals — never paid placement. How scoring works →
How DeepSeek Harness could raise its score
Each line changes one public signal and recomputes with the live scoring function. The gains don't add up exactly, because the score is capped near the top.
- Publish build provenance for its packagesnpm publish --provenance from CI +13.9 → 86.5 A · #6 of 75
- Raise the OSSF Scorecard from 4.6 to 9.0lowest checks: Branch-Protection 0, CII-Best-Practices 0, Code-Review 0 +9.1 → 81.7 A · #10 of 75
- Sign every commit0% signed today +5.0 → 77.6 B · #10 of 75
How DeepSeek Harness compares in Coding Agents
- #12 Ouroboros (Agent OS) 74.3 +1.7
- #13 GPTMe 73.0 +0.4
- #14 DeepSeek Harness 72.6 this agent
- #15 Tura 71.9 −0.7
- #16 Claude Code 70.8 −1.8
Bars show each HVTrust score; the tick marks DeepSeek Harness’s 72.6.
Where the 72.6 comes from
HVTrust dimensions vs the Coding Agents average
72.6 / 100 · 100.0% confidenceDeepSeek Harness Coding Agents average (75 agents)
Quick Trust Read
How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade B reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage B is separate — it grades how many independent signal types back the score (3 of 5), so a high score on thin evidence stays visible. Full methodology →
Rank Trend
Activity & Reach
Analysis
Activity Inputs
99.9 / 100Supply Chain Trust
Common questions about DeepSeek Harness
Does DeepSeek Harness publish package provenance?
Does DeepSeek Harness have an OpenSSF Scorecard?
Is DeepSeek Harness actively maintained?
What license does DeepSeek Harness use?
Are DeepSeek Harness's commits signed?
Not a safety endorsement. HVTracker describes what public signals show, not whether a project is safe for your use case. Run your own security review before adopting in production.
AI agent surface
MCP, providers, tool surface
These runtime-trust fields — detected from public repo docs and manifests — contribute a bounded adjustment to this project's HVTrust score alongside supply-chain evidence. The exact values each field can add or subtract are documented in the methodology → Compare this surface across every listed agent in the capability matrix →
- MCP signal live
- External deps live
- Tool / plugin surface live
- Package provenance drift live
Detected changes to DeepSeek Harness's runtime surface and supply-chain posture, from daily public-signal snapshots. A change here means our detectors see something different — a genuinely changed capability, or better evidence of an existing one.
Maintain DeepSeek Harness?
For maintainers
HVTrust scores DeepSeek Harness from public signals only — we never contact maintainers first. If a signal is wrong, stale, or missing (provenance you publish, a Scorecard you run, signed releases), tell us and we'll review it. Corrections are public and tracked on GitHub.
Reputation Timeline
Signal history
Embed Badge Badge guide for maintainers →
For maintainers
[](https://hvtracker.net/agents/deepseek-harness)
<a href="https://hvtracker.net/agents/deepseek-harness"><img src="https://hvtracker.net/badge/deepseek-harness.svg" alt="HVTrust"></a>
Other agents in Coding Agents
GitHub REST API (repo, commits, stars, forks, license) · npm Registry (downloads, provenance) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON