Superagent
Website
Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.
Is Superagent safe? Thin or incomplete trust evidence. Review carefully before production use.
Compare Superagent
How does it stack up against its Workflow Platforms neighbours?
Pick any agent to compare →In detail: Superagent scores 53.8/100 (Grade C), ranked #839 of 1371 tracked open-source AI agent projects, on evidence coverage A (4 of 5 independent signal types). The public evidence: no package-provenance attestation found; OSSF Scorecard rates its supply-chain practices 3.6/10; 56% of recent commits are signed; no published advisory affects its latest release (safety-agent); last pushed 2026-08-25. Every point is earned from checkable signals — never paid placement. How scoring works →
How Superagent 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 +14.7 → 68.5 B · #8 of 26
- Raise the OSSF Scorecard from 3.6 to 9.0lowest checks: CII-Best-Practices 0, Dependency-Update-Tool 0, Fuzzing 0 +11.3 → 65.1 B · #13 of 26
- Sign every commit56% signed today +2.2 → 56.0 C · #19 of 26
Chain of custody
Scanners check what the code says. This traces who ships Superagent and whether that has changed: from the source repository, through how changes are reviewed and released, to the package you install. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities.
-
Source Partly signed
github.com/superagent-ai/superagent, MIT, last pushed 2026-08-25. 56% of the last 100 commits carry a verified signature; the rest can't be tied to a verified identity.
-
Review and release Weak
OpenSSF Scorecard rates the repository's practices 3.6/10 (scanned Oct 4, 2026). The checks that decide who can get a change released:
- Code Review2
- Branch Protection3
- Signed Releases0
- Dangerous Workflow10
- Token Permissions0
- Pinned Dependencies0
All 18 Scorecard checks
Binary-Artifacts 10Branch-Protection 3CI-Tests 3CII-Best-Practices 0Code-Review 2Contributors 6Dangerous-Workflow 10Dependency-Update-Tool 0Fuzzing 0License 10Maintained 7Packaging -1Pinned-Dependencies 0SAST 0Security-Policy 10Signed-Releases 0Token-Permissions 0Vulnerabilities 0 -
Published packages Linked, not attested
- npm safety-agent Source link points back to this repo No build attestation
- PyPI superagent-py Source link isn't a GitHub repo No build attestation
Without a build attestation, nothing proves the published files were built from this repository.
-
What you install today No known advisories
Latest release checked: safety-agent 0.1.7. No published advisory affects it (OSV, checked 2026-10-09).
Changes to this chain
- 2026-10-02 Provenance drift warning cleared (now: unknown)
Evidence behind this score
Coverage A: 4 of 5 independent evidence types found.
- GitHub repository data
- Package downloads
- Supply-chain checks
- Public actions (missing)
- Community mentions
Verify this score yourself
Every build re-issues Superagent’s score as an Ed25519-signed credential, valid for 7 days. You can check it offline against HVTracker’s published key; if anyone changes a number after signing, verification fails.
What this score doesn’t check
It covers who ships the code, not what the code does. It doesn’t read tool descriptions or prompts for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you connect it, such as Cisco MCP Scanner or Snyk Agent Scan.
How Superagent compares in Workflow Platforms
- #18 Xpert AI 56.9 +3.1
- #19 BISHENG 55.5 +1.7
- #20 Superagent 53.8 this agent
- #21 Astron Agent 52.3 −1.5
- #22 Coze Studio 51.2 −2.6
Bars show each HVTrust score; the tick marks Superagent’s 53.8.
Where the 53.8 comes from
HVTrust dimensions vs the Workflow Platforms average
53.8 / 100 · 100.0% confidenceSuperagent Workflow Platforms average (26 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 C reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage A is separate — it grades how many independent signal types back the score (4 of 5), so a high score on thin evidence stays visible. Full methodology →
Rank Trend
Activity & Reach
Analysis
Activity Inputs
55.8 / 100Common questions about Superagent
Does Superagent publish package provenance?
Does Superagent have an OpenSSF Scorecard?
Is Superagent actively maintained?
What license does Superagent use?
Are Superagent'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 Superagent'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 Superagent?
For maintainers
HVTrust scores Superagent 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/superagent)
<a href="https://hvtracker.net/agents/superagent"><img src="https://hvtracker.net/badge/superagent.svg" alt="HVTrust"></a>
Other agents in Workflow Platforms
GitHub REST API (repo, commits, stars, forks, license) · npm Registry (downloads, provenance) · PyPI / pypistats (downloads, provenance) · OpenSSF Scorecard CLI · Algolia HN Search API
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON