Technology & Software Engineering Top 100 / #12ARD = Agentic Resource Discovery · A2A = Agent2Agent · MCP = Model Context Protocol

Coding agent · commercial · CLI; GitHub integrations

Claude Code

Widely used terminal coding agent with strong tool-use and ecosystem integrations. Publisher: Anthropic. Also ranked in Cybersecurity (#27), Supply Chain, Manufacturing & Logistics (#29), Sales, Marketing & Customer Experience (#32).

Vendor page ↗+ CompareExport JSON

Trust profileas of 2026-10-26

Publisherlikely · Repository ownership or inferred publisher domain — repository or Hub account ownershiplikely

Complianceno evidence about this agent · 2 vendor-level records (inherited)T5

Security49 CVEs linked in the registry · 40 critical/high · newest 2026-10-23linked

ProtocolsModel Context Protocol (MCP) probed, not foundAgent2Agent (A2A) probed, not foundAgentic Resource Discovery (ARD) probed, not found0 / 3

Traces1 public trace · best: vendor report · data left the environment in at least oneT3

Issues found0 regulator actions · 0 incidents · 0 withdrawn certificates · CVEs: see Securitylinks only

Publisher unconfirmed: the evidence below is shown but not counted in the governance score, because nothing yet ties this listing to Anthropic beyond repository or Hub account ownership. A vendor-domain page, marketplace listing, ARD manifest or A2A card would confirm it.

Evidence available — not a safety certification. Suitability depends on your task, deployment and permissions. Rows marked vendor-level describe Anthropic, not this agent specifically.

Traces — under attack, in defence, in incidents

1 public · what a trace is

⚠

real-world incident

T3 vendor report · unreviewed

Anthropic: a state-sponsored group used Claude Code to run most of an intrusion campaign autonomously

Operators jailbroke the agent by presenting tasks as legitimate security testing and had it perform reconnaissance, exploitation, credential harvesting and exfiltration against ~30 targets

Observed: Agent acted as the attacker across the campaign; Anthropic banned the accounts and published the report. A trace of the agent attacking, not defending · egress: yes · human approval: no · refused: no

Vendor response: Accounts banned; detection and classifier changes described in the report

Anthropic (vendor report)
2025-11-13

● third-party or vendor report · ◎ this registry's own probe transcript · ⚠ data left the environment. A trace describes one version on one date; it is evidence of behaviour, never a certification. Rows marked unreviewed have not yet been checked against their source by the maintainer.

CVEs — on the official record

49 linked · the registry

CVE-2026-99042

2026-10-23

In the Linux kernel, the following vulnerability has been resolved: io_uring/net: populate CONNECT filter fields for 24-byte sockaddr_in6 io_connect_bpf_populate() fills connect.p…

— · unreviewed

High 8.4

CVE-2026-96620

2026-10-16

Claude Agent SDK is a Python SDK for Claude Code. Prior to 0.2.121, the resume option is passed to the Claude CLI as a separate token without validation, so a dash-leading value i…

Code execution · Tool execution · unreviewed

Critical 9.2

CVE-2026-86063

2026-10-13

Claude Code is an agentic coding tool. Prior to 2.1.179, the Claude Code and Claude Desktop plugin installation flow runs git checkout for a marketplace-pinned commit without veri…

Supply chain · unreviewed

High 7.5

CVE-2026-103435

2026-10-07

Claude Code validated that a target file path resided within the project working directory at permission-check time, but re-resolved the path at write time without repeating that…

Path traversal · unreviewed

High 7.7

CVE-2026-103012

2026-09-30

Claude Code selected an API key stored by Claude Code, for example from an earlier `/login` or written directly to its configuration, ahead of the user's valid Claude Enterprise o…

Credential access · unreviewed

Low 2.0

CVE-2026-100585

2026-09-26

OpenClaw (npm package `openclaw`) before 2026.7.1 fails to enforce the owner-only authorization requirement for Claude Code permission prompts delivered through the MCP channel br…

Auth bypass · unreviewed

High 8.6

CVE-2026-49986

2026-08-14

The Cortex MCP server (`neuro-cortex-memory`), a cross-platform persistent memory MCP, prior to version 3.17.1 treats the `CLAUDE_PROJECT_DIR` environment variable — automatically…

Code execution · Tool execution · Supply chain · unreviewed

High 7.1

CVE-2026-73614

2026-08-13

Network-AI ClaudeHookBridge before 5.15.1 truncates the target string to 500 characters before evaluating denyPatterns, while Claude Code executes the full untruncated command. At…

Code execution · unreviewed

High 8.7

41 more · All 49 in the registry → Severity is the official record's; nothing here enters the score. Links are by listed product, so a CVE that names a different component of the same platform may be missing.

Compliance evidence

Jurisdiction: EU · 5 frameworks shown

–

SOC 2

T5 Unknown

Nothing found in the sources checked.

Scope: — · registries, marketplaces, vendor pages

ask the vendor

–

ISO 27001

T5 Unknown

Nothing found in the sources checked.

Scope: — · registries, marketplaces, vendor pages

ask the vendor

–

CSA STAR

T5 Unknown

Nothing found in the sources checked.

Scope: — · CSA STAR Registry

ask the vendor

"Unknown" means nothing was found in the sources checked — registries, marketplaces and the vendor's own pages. It is not a finding of non-compliance; ask the vendor.

About the vendor — inherited, not agent-specific

2 records matched at organisation level

✔

ISO 42001 · ISO 42001

T1 Registry-matched · vendor-level

Found in CSA STAR Registry on 2026-10-26

Scope: entity · CSA STAR Registry · 2026-10-26

re-check 2026-11-02

○

GDPR · DPA available

T4 Vendor-claimed · vendor-level

Vendor-claimed

Scope: entity · vendor page · 2026-10-26

re-check 2026-11-02

A vendor-level registry entry proves the organisation was assessed; whether this agent is inside that scope is a question for the vendor. These rows do not count toward the agent's evidence tier.

✔ found · ○ claimed · – not found · ⚠ expired, stale or revoked. Every row links to its source.Dispute or correct this dossier

GDPR, assembled from checks

GDPR● 0 found in registries or documents○ 1 vendor-claimed⚠ 0 issues linkedas of 2026-10-26

○ ClaimedDPA available: Vendor-claimed (vendor page, 2026-10-26). A DPA is a contract you still have to sign and review.

– Not foundNo Article 42 GDPR seal. "GDPR certified" is never shown without one.

☐ You checkYour lawful basis, DPIA, and whether this agent is inside the certificate scope.

News and chatter

last 90 days · linked with confidence ≥ 0.85

2026-10-23

claude-code release v2.1.310

GitHub releases · ## What's changed - Added the Monitor tool and plugin monitors on Bedrock, Vertex, and Foundry, and when telemetry or nonessential traffic is disabled; long foreground sleeps are now blocked there too - Fixed requests failing behind some g

Product update

2026-10-22

claude-code release v2.1.309

GitHub releases · ## What's changed - Fixed sandboxed Bash commands on macOS and Linux running the shell's startup files outside the sandbox before each command - Fixed macOS sandbox `denyWrite` glob patterns not applying at a path's real location when the

Product update

Headline, link and a summary attributed to the outlet. News never changes trust or domain scores.

Technology & Software Engineering score

technology profile · sar-score-2.0 · #12 of 100 in the curated list

Adoption / usage29 / 30

Trust & security16 / 25

Project / product health20 / 20

Ecosystem / interoperability14 / 15

Domain expertise / fit38 / 100

Governance / compliance evidence0 / 100

Docs / transparency10 / 10

Raw component / maximum, then weighted by the technology profile (adoption 30, trust 20, project 20, ecosystem 15, domain 10, governance 0, docs 5). Trust and governance are computed from the evidence on this page (vendor-level rows at half credit); the other components come from the curated workbook, whose order is the rank. Unknown components count as 0 and are never imputed.

Before you deploy

Deployment questions answered from the vendor's documentation, each with its source.

✔Reads private repositories? Yes — Runs in the project directory on your machine; file tools are bounded to that folder in Manual mode source

✔Executes code or writes changes? Yes — "Manual mode: Claude Code starts with read-only permissions. When it needs to edit files, run tests, or execute commands, it asks you first" source

◐Credential handling documented? Configurable — "API keys and tokens are stored in the macOS Keychain when available"; sandboxed bash with filesystem and network isolation; in cloud sessions "GitHub credentials ... never enter the session VM" source

✔Can run entirely on your own machine or infrastructure? Yes — Local terminal process; optional sandbox runtime or dev container; cloud sessions can be routed to a self-hosted environment source

◐Human approval before consequential actions? Configurable — Manual mode asks before edits and commands; Auto mode delegates to a classifier; Accept Edits mode auto-approves edits. "You're responsible for reviewing proposed code and commands for safety before approval" source

Evidence supporting this use (7)

ISO 42001 — registry-matched, vendor-level source

GDPR DPA available — vendor-claimed, vendor-level source

Reads private repositories: yes — Runs in the project directory on your machine; file tools are bounded to that folder in Manual mode source

Executes code or writes changes: yes — "Manual mode: Claude Code starts with read-only permissions. When it needs to edit files, run tests, or execute commands, it asks you first" source

Credential handling documented: configurable — "API keys and tokens are stored in the macOS Keychain when available"; sandboxed bash with filesystem and network isolation; in cloud sessions "GitHub credentials ... never enter the session VM" source

Can run entirely on your own machine or infrastructure: yes — Local terminal process; optional sandbox runtime or dev container; cloud sessions can be routed to a self-hosted environment source

Human approval before consequential actions: configurable — Manual mode asks before edits and commands; Auto mode delegates to a classifier; Accept Edits mode auto-approves edits. "You're responsible for reviewing proposed code and commands for safety before approval" source

Unknowns to check (4)

Your lawful basis and DPIA for PHI and personal data the agent will touch

The transfer mechanism you will rely on; DPF covers EU-to-US transfers only

Ask the vendor for SOC 2, ISO 27001, CSA STAR evidence; none was found in the sources checked

Whether the agent exposes MCP or A2A endpoints; none were observed

Suggested restrictions for a pilot (3)

Limit the pilot to one non-production repository with a protected default branch; let the agent push to one branch only.

Ask for the SOC 2 report under NDA before the pilot touches customer data; none was found in the sources checked.

A public trace shows data leaving the environment under adversarial input. Confirm the vendor's fix is in the version you deploy, and keep an egress allowlist around the agent during the pilot.

See the worked comparison: Three ways to let a coding agent into a private repository →

Rules: config/deploy_rules.json. Advice for a bounded pilot, not a verdict.

Provenance

seed workbookscores, rank, category

CSA STAR Registrycompliance evidence

vendor pageclaims

NVDsecurity (CVE keyword search)

Hacker News, GDELT, vendor feedsnews and chatter

First seen2026-10-26

Recordres_97cd54bb05e797a4

Open the full record (JSON) →

Traces — under attack, in defence, in incidents

CVEs — on the official record

Compliance evidence

About the vendor — inherited, not agent-specific

GDPR, assembled from checks

News and chatter

Technology & Software Engineering score

Before you deploy

Provenance

Appears in the incident registry