agentlint
Audit any website for AI/agent-friendliness using AgentLint. Run `npx @cjavdev/agent-lint` with a URL to scan a site across 17 rules in 5 categories (transport, structure, tokens, discoverability, agent), get a 0-100 AgentScore with letter grade, and receive a prioritized remediation plan. Use this skill when: auditing a site for AI readiness, checking if a site has llms.txt or markdown support, improving a website's agent-friendliness score, fixing AgentLint violations, or understanding what makes a site AI-friendly. Trigger phrases: 'run agentlint', 'audit site for AI', 'check agent-friendliness', 'agentlint scan', 'AI-friendly audit', 'check llms.txt', 'agent readiness'.
100
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Security
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs running `npx @cjavdev/agent-lint <url> --agent` to crawl and fetch pages (including /llms.txt, sitemap, OpenAPI paths, and page contents) from arbitrary public websites, so the agent will ingest untrusted third‑party web content that can influence its remediation decisions and next actions.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.80). The skill's runtime requires running "npx @cjavdev/agent-lint", which will fetch and execute the @cjavdev/agent-lint package from the npm registry (e.g., https://www.npmjs.com/package/@cjavdev/agent-lint), so it relies on external code fetched and run at runtime.
- Repository
- cjavdev/agent-lint
- Commit
04dcd58
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.