Agent Skills State 2026 — Security skill for Claude Code
Study of 2,999 public agent skill, plugin and MCP repositories (October 2026): missing security policies, unpinned MCP servers, unrestricted shell in skills, front matter that fails to parse.
How to install Agent Skills State 2026
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open basitalisandhu/agent-skills-state-2026 and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Agent Skills State 2026 does
Study of 2,999 public agent skill, plugin and MCP repositories (October 2026): missing security policies, unpinned MCP servers, unrestricted shell in skills, front matter that fails to parse. Dataset (CC BY 4.0), method, hand-checked precision and scripts.
Alternatives in Security
- Security Guardian — Comprehensive security analysis for RTK CLI tool, focusing on command injection, shell escaping, hook security 11.9k ★
- Curate Security Results — Run Security Tests & Curate Results — Public-Safe Snapshots 295 ★
- Public Skills Builder — Generate Claude Code bug bounty skills from public HackerOne reports and GitHub writeups — 18 vuln classes, no 155 ★
README
The state of public agent skills and MCP servers, October 2026
*Muhammad Basit Ali, 13 October 2026. Dataset, method and scripts are in this repository. Data and text: CC BY 4.0. Code: MIT.*
*This is the first edition. The scan is re-run every month and each month's data is added alongside; see [Updated monthly](#updated-monthly).*
Agent skills, plugin marketplaces and MCP servers are now installed the way browser extensions once were: someone finds a repository, copies a line into a config file and the agent gains new instructions, new shell access or a new process that starts with every session. We wanted to know what that supply looks like on the ground, measured rather than guessed. So we took a random sample of 2,999 public GitHub repositories that ship a `SKILL.md`, a plugin or marketplace manifest, or an MCP `server.json`, scanned them with open-source tools, and hand-checked the scanners before trusting them.
Key findings
- No way to report a vulnerability: 2,459 of 2,999 (82.0%) repositories have no
SECURITY.md. Among the 434 with 100 or more stars it is still 75.6%. - MCP servers that can change under you: 159 of 346 (46.0%) repositories that configure a local MCP server start at least one with no pinned version; 63 of 346 (18.2%) ask for the
latesttag outright. - No licence: 982 of 2,999 (32.7%) have no licence file at the root.
- The whole shell: 407 of 2,621 (15.5%) repositories with skills give at least one skill unscoped
Bash, 10,073 declarations in all. - Skill headers that do not parse: in 330 of 2,621 (12.6%) repositories with skills, at least one
SKILL.mdhas front matter a standard YAML parser rejects; that is 4,761 of 336,285 (1.4%) files.
Every number in this list is checked against [`data/2026-10/stats.json`](data/2026-10/stats.json) in CI by [`scripts/check_numbers.py`](scripts/check_numbers.py).
Updated monthly
This study is a monthly index. On the 1st of each month at 03:00 UTC a scheduled workfl
Related Skills
Auditthesis
Audit a UQAC Master's or PhD thesis (LaTeX, uqac.cls): front matter compliance, hypothesis flow across all cha
API Security
API security audit (OWASP API Security Top 10 2023): BOLA/IDOR, broken authentication, broken object-property-
Audit Agent Friendly
Run the AGENT_READINESS_CHECKLIST.md against a page (or the whole site) and report what fails.
Token Waste Audit
Run the FR-26 token-waste audit — parse this project's Claude Code transcripts deterministically (requestId-de
09 Technical Roadmap
Parse Screaming Frog crawl, audit AI crawler access, SSR, IndexNow, schema; output prioritized technical roadm
Causal Design
Design or audit the identification strategy for an observational study.
Related Agents
Thesis Auditor
Use when the user provides a UQAC Master's or PhD thesis (LaTeX, uqac.cls) and wants a full institutional and
Cortex Graph Auditor
Audits the quality of a Córtex analysis (community coherence, unresolved imports and calls, parse warnings, mi
Light Security ClaudeSettingsAudit
Audit Claude Code config files (settings.json, settings.local.json, .mcp.json) for unsafe or malicious content