Giskard
Website
🐢 Open-Source Evaluation & Testing library for LLM Agents
Is Giskard safe? Promising trust profile, but some evidence still deserves review.
Compare Giskard
How does it stack up against its Observability & Evaluation neighbours?
Pick any agent to compare →In detail: Giskard scores 67.4/100 (Grade B), ranked #410 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 6.8/10; 77% of recent commits are signed; last pushed 2026-10-09. Every point is earned from checkable signals — never paid placement. How scoring works →
How Giskard 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 packagesPyPI Trusted Publishing attestations +14.7 → 82.1 A · #6 of 26
- Raise the OSSF Scorecard from 6.8 to 9.0lowest checks: CII-Best-Practices 0, Dangerous-Workflow 0, Fuzzing 0 +4.6 → 72.0 B · #10 of 26
- Sign every commit77% signed today +1.2 → 68.6 B · #11 of 26
Chain of custody
Scanners check what the code says. This traces who ships Giskard 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/Giskard-AI/giskard-oss, Apache-2.0, last pushed 2026-10-09. 77% of the last 100 commits carry a verified signature; the rest can't be tied to a verified identity.
-
Review and release Mixed
OpenSSF Scorecard rates the repository's practices 6.8/10 (scanned Oct 4, 2026). The checks that decide who can get a change released:
- Code Review4
- Branch Protection8
- Signed Releases0
- Dangerous Workflow0
- Token Permissions10
- Pinned Dependencies10
All 18 Scorecard checks
Binary-Artifacts 10Branch-Protection 8CI-Tests 10CII-Best-Practices 0Code-Review 4Contributors 10Dangerous-Workflow 0Dependency-Update-Tool 10Fuzzing 0License 10Maintained 10Packaging -1Pinned-Dependencies 10SAST 10Security-Policy 10Signed-Releases 0Token-Permissions 10Vulnerabilities 8 -
Published packages Not linked
- PyPI giskard Source link isn't a GitHub repo No build attestation
Without a build attestation, nothing proves the published files were built from this repository.
Changes to this chain
No change to package provenance, package source links, Scorecard coverage or license in HVTracker's daily snapshots of Giskard.
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 Giskard’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 Giskard compares in Observability & Evaluation
- #10 DeepEval 69.4 +2.0
- #11 Agenta 68.2 +0.8
- #12 Giskard 67.4 this agent
- #13 Holmesgpt 65.6 −1.8
- #14 Helicone 62.9 −4.5
Bars show each HVTrust score; the tick marks Giskard’s 67.4.
Where the 67.4 comes from
HVTrust dimensions vs the Observability & Evaluation average
67.4 / 100 · 100.0% confidenceGiskard Observability & Evaluation 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 B 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
78.4 / 100Common questions about Giskard
Does Giskard publish package provenance?
Does Giskard have an OpenSSF Scorecard?
Is Giskard actively maintained?
What license does Giskard use?
Are Giskard'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
Maintain Giskard?
For maintainers
HVTrust scores Giskard 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/giskard)
<a href="https://hvtracker.net/agents/giskard"><img src="https://hvtracker.net/badge/giskard.svg" alt="HVTrust"></a>
Other agents in Observability & Evaluation
GitHub REST API (repo, commits, stars, forks, license) · 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