Claude Red
claude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a specific attack surface — from SQLi to shellcode, EDR evasion to exploit development.
Is Claude Red safe? Promising trust profile, but some evidence still deserves review.
Compare Claude Red
How does it stack up against its Agent Skills neighbours?
Pick any agent to compare →In detail: Claude Red scores 57.4/100 (Grade C), ranked #142 of 384 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 6.2/10; 80% of recent commits are signed; last pushed 2026-10-12. Every point is earned from checkable signals — never paid placement. How scoring works →
How Claude Red 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.
- Raise the OSSF Scorecard from 6.2 to 9.0lowest checks: Branch-Protection 0, CII-Best-Practices 0, Dependency-Update-Tool 0 +5.8 → 63.2 C · #77 of 384
- Sign every commit80% signed today +1.0 → 58.4 C · #129 of 384
Chain of custody
Scanners check what the code says. This traces who ships Claude Red and whether that has changed: from the source repository, through how changes are reviewed and released, to the code you run. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities and, for skills, AST02 Supply Chain Compromise.
-
Source Signed
github.com/SnailSploit/Claude-Red, MIT, last pushed 2026-10-12. 80% of the last 100 commits carry a verified signature, so changes trace to a verified account.
-
Review and release Mixed
OpenSSF Scorecard rates the repository's practices 6.2/10 (scanned Nov 6, 2026). The checks that decide who can get a change released:
- Code Review3
- Branch Protection0
- Signed Releasesn/a
- Dangerous Workflow10
- Token Permissions8
- Pinned Dependencies3
All 18 Scorecard checks
Binary-Artifacts 10Branch-Protection 0CI-Tests 8CII-Best-Practices 0Code-Review 3Contributors 6Dangerous-Workflow 10Dependency-Update-Tool 0Fuzzing 0License 10Maintained 10Packaging -1Pinned-Dependencies 3SAST 9Security-Policy 10Signed-Releases -1Token-Permissions 8Vulnerabilities 10 -
Published packages None
No registry package. Claude Red is used from its repository, so what you run is whatever you check out: pin a release tag or commit.
Changes to this chain
- 2026-08-28 OSSF Scorecard: 5.8/10
Evidence behind this score
Coverage C: 2 of 5 independent evidence types found.
- GitHub repository data
- Package downloads (missing)
- Supply-chain checks
- Public actions (missing)
- Community mentions (missing)
Verify this score yourself
Every build re-issues Claude Red’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 the skill’s instructions for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you install it, such as Cisco Skill Scanner.
How Claude Red compares in Agent Skills
- #140 Mattpocock Skills 57.5 +0.1
- #141 Makerskills 57.5 +0.1
- #142 Claude Red 57.4 this agent
- #143 Openbrowser Ai 57.3 −0.1
- #144 Goose Skills 57.2 −0.2
Bars show each HVTrust score; the tick marks Claude Red’s 57.4.
Where the 57.4 comes from
HVTrust dimensions vs the Agent Skills average
57.4 / 100 · 100.0% confidenceClaude Red Agent Skills average (384 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 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
Activity & Reach
Analysis
Activity Inputs
63.7 / 100Common questions about Claude Red
Does Claude Red publish package provenance?
Does Claude Red have an OpenSSF Scorecard?
Is Claude Red actively maintained?
What license does Claude Red use?
Are Claude Red'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 Claude Red'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 Claude Red?
For maintainers
HVTrust scores Claude Red 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/claude-red)
<a href="https://hvtracker.net/agents/claude-red"><img src="https://hvtracker.net/badge/claude-red.svg" alt="HVTrust"></a>
Other agents in Agent Skills
GitHub REST API (repo, commits, stars, forks, license) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON