Is Agent-S safe?
Agent-S scores 41.3/100 (Grade D), ranked #357 of 418 tracked open-source AI agent projects, on evidence coverage C (2 of 5 independent signal types).
The public evidence: no package-provenance attestation found;
OSSF Scorecard rates its supply-chain practices 3.8/10;
recent commits are unsigned;
last pushed 2026-05-13. Every point is earned from checkable signals — never paid placement. How scoring works →
Quick Trust Read
Verdict
Thin or incomplete trust evidence. Review carefully before production use.
41.3/100 · Grade D
Strongest Signal
Transparency
11.7/17
Weakest Signal
Safety / Integrity
4.8/25
What Would Improve It
Publish package provenance or release attestations for stronger supply-chain evidence.
Recent Changes
2026-07-15
Rank Moved
Rank dropped 27 spots (#326 → #353)
2026-07-14
Rank Moved
Rank dropped 15 spots (#311 → #326)
2026-07-13
Rank Moved
Rank dropped 37 spots (#274 → #311)
Maintainer Checklist
Raise Scorecard signalsCurrent OSSF Scorecard is 3.8/10. Tighten the weakest checks to improve public safety evidence.
Publish provenanceAdd package provenance or release attestations so users can verify where shipped artifacts came from.
Increase signed commitsRaise the share of verified-signed commits to make maintainer identity and release history easier to trust.
Refresh maintenance signalsThe repo was last pushed 70 days ago. Fresh activity helps separate stable projects from stale ones.
How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade D reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage C is separate — it grades how many independent signal types back the score (2 of 5), so a high score on thin evidence stays visible. Full methodology →
Signals refreshed2026-07-22 22:03 UTC·Repo last pushed 70 days ago
Public trust evidence for Agent-S is thin: several supply-chain signals are missing or weak. This does not mean the project is unsafe — it means an outside observer cannot easily verify the usual integrity checks. Treat with extra scrutiny.
Does Agent-S publish package provenance?
No published build provenance is currently detected for Agent-S. This is common for open-source projects but means consumers cannot independently verify that the package on the registry matches the GitHub source.
Does Agent-S have an OpenSSF Scorecard?
Agent-S has an OpenSSF Scorecard score of 3.8/10. The Scorecard checks for branch protection, signed releases, dependency updates, fuzzing, code review, and other supply-chain hygiene items. See the full check breakdown on this page.
Is Agent-S actively maintained?
Slowing down. Last push was 70 days ago — keep an eye on whether activity resumes.
What license does Agent-S use?
Agent-S ships under Apache-2.0. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
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.
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 Server Support
None detected
No MCP server signal detected.
Detailed evidence is not shown in the public view.
Credential signal:
API keys or service config markers documented.
Tool / Plugin Surface
high confidence
2 tags
Broad capability areas detected.
browser
code
Detailed evidence is not shown in the public view.
Package Provenance Drift
N/A
No package source configured
Detailed evidence is not shown in the public view.
MCP signal live
External deps live
Tool / plugin surface live
Package provenance drift live
Maintain Agent-S?
HVTrust scores Agent-S 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.
Data sources
GitHub REST API (repo, commits, stars, forks, license) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.2 · Raw JSON
