Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
/plugin marketplace add Zyoffsec/airtight-secure-codingnpx agentmods add plugins/zyoffsec/airtight-secure-coding/marketplacegit clone --depth 1 https://github.com/Zyoffsec/airtight-secure-codingGrade A, and why
airtight scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
"name": "airtight",
"description": "Secure-coding gates for AI-written code",
"owner": {
"name": "Zy"
},
"plugins": [
{
"name": "airtight",
"description": "Secure-coding gates for AI-written code: 70 numbered gates mapped to OWASP Top 10 and CWE, plus a pre-write guard that stops the write when it can prove the failure.",
"version": "0.3.5",
"author": {
"name": "Zy"
},
"source": "./",
"category": "security",
"homepage": "https://github.com/Zyoffsec/airtight-secure-coding"
}
]
}
What ships with it
1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 22 lines scan A 713fa9a092a2
airtight is a plugin published in the GitHub repository Zyoffsec/airtight-secure-coding (6 stars, last pushed 28d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
penthera
Plugin marketplace listing 1 plugin: penthera.
penthera
Find and fix security issues in vibecoded apps. Scan a live URL, a local repo, or your macOS machine for TLS, headers, auth, secrets, IDOR/OAuth, and injection issues, then apply framework-aware fixes and re-scan to verify. Mapped to OWASP with SARIF output. Runs as a skill or CLI. Authorized testing only.
vantage
Artifact-driven, plugin-based multi-agent SAST pipeline for web and mobile app repositories. Web agents cover the OWASP Top 10; mobile agents cover the OWASP Mobile Top 10 (2024, M1-M10). Both share global validation/PoC/reporting agents. Run /vantage:scan-web or /vantage:scan-mobile to scan, then /vantage:fix-issue…
vantage
Marketplace for the vantage AI SAST plugin (web + mobile pentest pipeline).
shipcheck
Pre-launch risk scanner for AI-built apps. Flags exposed secrets, copyleft-licensed dependencies, unauthenticated data endpoints, missing privacy/consent artifacts, and client-side payment handling before you ship.
shipcheck-marketplace
Plugin marketplace listing 1 plugin: shipcheck.