seo-schema
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection because it is designed to ingest and analyze untrusted data from external websites.
- Ingestion points: The skill reads page source code from user-provided URLs via the
[url]argument. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the guidelines.
- Capability inventory: The skill is capable of reading external content and generating JSON-LD templates based on that content.
- Sanitization: There is no evidence of content sanitization or validation logic in the provided instructions.
- [EXTERNAL_DOWNLOADS]: The license file mentions the author's GitHub repository (
https://github.com/AgriciDaniel/claude-seo). This is a legitimate reference to a vendor-owned resource for documentation and source code and does not represent a security risk.
Audit Metadata