html-seo-review
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses a provided Python script (
scripts/extract_seo_signals.py) to analyze HTML content. The script is well-documented, follows clean coding practices, and is restricted to the Python standard library, requiring no external packages or remote downloads. - [SAFE]: No network operations, data exfiltration patterns, or hardcoded credentials were identified. The script operates exclusively on local files provided by the user.
- [SAFE]: The instructions in
SKILL.mdprovide a structured workflow that mitigates common LLM errors (like hallucinations) by requiring the agent to cite exact line numbers and use structured JSON output from the parser rather than skimming raw HTML. - [SAFE]: No obfuscation techniques, hidden commands, or privilege escalation patterns were found in any of the skill's files.
- [SAFE]: While the skill ingests untrusted HTML data for review, it implements sound boundary management by converting HTML into a structured JSON schema before the agent processes the findings, reducing the surface area for indirect prompt injection.
Audit Metadata