Scan Report
0 /100
er
AI4L Evidence Review Toolkit — generates and QA-audits health/longevity evidence reviews
The AI4L Evidence Review Toolkit is a purely document-generation and QA auditing skill with no executable code, no shell access, no sensitive file access, and no network exfiltration capability. All declared capabilities are appropriate for its stated purpose.
Safe to install
This skill is safe to use as-is. No security restrictions or modifications are needed.
| Resource | Declared | Inferred | Status | Evidence |
|---|---|---|---|---|
| Filesystem | WRITE | WRITE | ✓ Aligned | SKILL.md: 'All generated results go in ./results/' |
| Filesystem | READ | READ | ✓ Aligned | SKILL.md: targets AI4L.md, CLAUDE.md, README.md, etc. |
| Network | READ | READ | ✓ Aligned | AI4L.md auditor instructions require PubMed lookups and URL verification |
| Shell | NONE | NONE | — | No shell or subprocess usage declared or inferred |
| Environment | NONE | NONE | — | No environment variable access detected |
| Database | NONE | NONE | — | No database access declared or inferred |
| Clipboard | NONE | NONE | — | No clipboard access detected |
| Browser | NONE | NONE | — | No browser automation detected |
4 findings
Medium External URL 外部 URL
https://forever-healthy.org AI4L.md:1 Medium External URL 外部 URL
https://img.shields.io/badge/version-2026.03.19.1-green.svg AI4L.md:5 Medium External URL 外部 URL
https://pubmed.ncbi.nlm.nih.gov/PMID/ AI4L.md:288 Medium External URL 外部 URL
https://clinicaltrials.gov/study/\ AI4L.md:665 File Tree
2 files · 44.3 KB · 923 lines Markdown 2f · 923L
├─
AI4L.md
Markdown
└─
SKILL.md
Markdown
Security Positives
✓ No executable code — skill is pure Markdown documentation with zero scripts or binaries
✓ All declared capabilities (read AI4L.md, write to ./results/) are appropriate and minimal for the task
✓ No shell, subprocess, or command execution capabilities declared or present
✓ No credential harvesting, environment variable enumeration, or sensitive path access
✓ No obfuscation techniques (base64, eval, atob) detected
✓ No supply chain risk — no dependencies, requirements.txt, package.json, or Cargo.toml
✓ Network access is limited to legitimate evidence-audit-related searches (PubMed, clinicaltrials.gov, expert sources)
✓ No data exfiltration — skill only generates documents locally in ./results/
✓ Open-source tool by a known health foundation (Forever Healthy Foundation)
✓ Well-structured, explicit documentation with clear operational boundaries