Is Adversarial Spec safe to use?

Adversarial Spec has an HVTrust score of 27.8/100 (Grade D), ranked #347 of 351 tracked AI agent projects. This score reflects verifiable supply-chain integrity, transparency, maintenance, and adoption signals.

What is the trust score for Adversarial Spec?

Adversarial Spec scores 27.8/100 on HVTracker's evidence-weighted HVTrust scale. It has 557 GitHub stars and is categorized under Agent Skills.

Adversarial Spec

zscole/adversarial-spec

A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until all models reach consensus.

Agent Skills Python Listed MIT

Is Adversarial Spec safe? Thin or incomplete trust evidence. Review carefully before production use.

OSSF Scorecard 2.6 / 10

Provenance None

Signed commits 15%

Last push 247d ago

Compare Adversarial Spec

How does it stack up against its Agent Skills neighbours?

Pick any agent to compare →

Suggest a correction

In detail: Adversarial Spec scores 27.8/100 (Grade D), ranked #347 of 351 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 2.6/10; 15% of recent commits are signed; last pushed 2026-01-22. Every point is earned from checkable signals — never paid placement. How scoring works →

How Adversarial Spec compares in Agent Skills

Bars show each HVTrust score; the tick marks Adversarial Spec’s 27.8.

Where the 27.8 comes from

HVTrust dimensions vs the Agent Skills average

27.8 / 100 · 100.0% confidence

Adversarial Spec Agent Skills average (351 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits

4.0 / 25

4.1 below avg 8.1

Identity / Provenance60% listing status · 40% build provenance

10.8 / 18

0.6 below avg 11.4

Transparency50% declared license · 50% OSSF Scorecard

10.7 / 17

1.5 below avg 12.2

Maintenance60% last-push freshness · 40% commit activity

0 / 20

14.2 below avg 14.2

AdoptionLog-scaled stars · package downloads

6.6 / 20

2.4 below avg 9.0

Quick Trust Read

What Would Improve It

Publish package provenance or release attestations for stronger supply-chain evidence.

Recent Changes

2026-09-25

HVTrust Changed

HVTrust up 10.7pts (17.1 → 27.8)

2026-09-23

Tool Surface Changed

Detected tool/plugin surface changed: none → declared

2026-09-23

Provider Added

Runtime surface grew — new detected provider dependencies: Anthropic, DeepSeek, Google Gemini, Groq, Mistral AI, Multi-provider (LiteLLM), OpenAI, OpenRouter, xAI Grok

Maintainer Checklist

Raise Scorecard signals Current OSSF Scorecard is 2.6/10. Tighten the weakest checks to improve public safety evidence.

Publish provenance Add package provenance or release attestations so users can verify where shipped artifacts came from.

Increase signed commits Raise the share of verified-signed commits to make maintainer identity and release history easier to trust.

Refresh maintenance signals The repo was last pushed 247 days ago. Fresh activity helps separate stable projects from stale ones.

Compare with another agent Get email alerts for Adversarial Spec View Agent Skills Report missing data

24.4

Activity sub-score · out of 100

#347

In Agent Skills

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 →

Rank Trend

2026-08-11 2026-09-26

Activity & Reach

Stars

557

Forks

Last Push

2026-01-22

247 days ago

Commits (4 wk)

Downloads (7d)

—

HN mentions (30d)

—

Open Issues

Rank Change

was #347

Analysis

Activity Inputs

24.4 / 100

StarsRepository reach

16.5 / 30

FreshnessLast push recency

0.0 / 25

ActivityRecent commits

0.0 / 25

CommunityFork signal

7.9 / 20

Supply Chain Trust

Package Provenance

None

No package attestations found

OSSF Scorecard

2.6 / 10

OpenSSF Scorecard · scanned Sep 22, 2026

Signed Commits

15%

of last 100 commits verified

Binary-Artifacts 10

Branch-Protection 0

CI-Tests 3

CII-Best-Practices 0

Code-Review 1

Contributors 10

Dangerous-Workflow 10

Dependency-Update-Tool 0

Fuzzing 0

License 10

Maintained 0

Packaging -1

Pinned-Dependencies 0

SAST 0

Security-Policy 0

Signed-Releases -1

Token-Permissions 0

Vulnerabilities 0

Common questions about Adversarial Spec

Public trust evidence for Adversarial Spec 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 Adversarial Spec publish package provenance?

No published build provenance is currently detected for Adversarial Spec. This is common for open-source projects but means consumers cannot independently verify that the package on the registry matches the GitHub source.

Does Adversarial Spec have an OpenSSF Scorecard?

Adversarial Spec has an OpenSSF Scorecard score of 2.6/10. 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 Adversarial Spec actively maintained?

Stale. The repository has not been pushed to in 247 days. Consider whether the project is still being maintained.

What license does Adversarial Spec use?

Adversarial Spec ships under MIT. A declared, OSI-approved license is one of the transparency signals HVTrust scores.

Are Adversarial Spec's commits signed?

14% of the last 100 commits to Adversarial Spec are verified-signed (GPG, SSH, S/MIME, or GitHub's signing flow). Signed commits help confirm that code was authored by who the commit claims.

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

Scored in HVTrust

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.

External Service Dependencies

high confidence

9 detected

Public provider/service dependencies detected.

Credential signal: API keys or service config markers documented.

Tool / Plugin Surface

high confidence

Declared

Declared plugin/integration surface detected.

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

How this surface has changed

Detected changes to Adversarial Spec'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.

2026-09-23

Tool Surface Changed

Detected tool/plugin surface changed: none → declared

2026-09-23

Provider Added

Runtime surface grew — new detected provider dependencies: Anthropic, DeepSeek, Google Gemini, Groq, Mistral AI, Multi-provider (LiteLLM), OpenAI, OpenRouter, xAI Grok

Maintain Adversarial Spec?

For maintainers

HVTrust scores Adversarial Spec 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.

Submit a correction → Add the trust badge

Reputation Timeline

Signal history

2026-09-25

HVTrust Changed

HVTrust up 10.7pts (17.1 → 27.8)

2026-09-23

Tool Surface Changed

Detected tool/plugin surface changed: none → declared

2026-09-23

Provider Added

Runtime surface grew — new detected provider dependencies: Anthropic, DeepSeek, Google Gemini, Groq, Mistral AI, Multi-provider (LiteLLM), OpenAI, OpenRouter, xAI Grok

2026-09-22

Newly Listed

First tracked at rank #349

2026-09-21

Removed From Active Tracking

Removed from active tracking

2026-09-08

Rank Moved

Rank dropped 21 spots (#326 → #347)

2026-09-05

Scorecard Added

OSSF Scorecard: 2.6/10

2026-09-05

HVTrust Changed

HVTrust up 10.8pts (6.3 → 17.1)

2026-08-26

Rank Moved

Rank dropped 171 spots (#159 → #330)

2026-08-16

Rank Moved

Rank dropped 11 spots (#148 → #159)

2026-08-11

Newly Listed

First tracked at rank #148

GitHub →

Embed Badge Badge guide for maintainers →

For maintainers

Markdown:
            [![HVTrust](https://hvtracker.net/badge/adversarial-spec.svg)](https://hvtracker.net/agents/adversarial-spec)
            
HTML:
            <a href="https://hvtracker.net/agents/adversarial-spec"><img src="https://hvtracker.net/badge/adversarial-spec.svg" alt="HVTrust"></a>

Other agents in Agent Skills

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 v4.3 · Raw JSON