seo-schema
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external web content (JSON-LD, Microdata, RDFa) to detect and validate schema markup. This creates a potential surface for indirect prompt injection if a processed page contains malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill scans page source code for various structured data formats as described in
SKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or "ignore" warnings when processing external data.
- Capability inventory: The skill generates analysis reports (
SCHEMA-REPORT.md) and JSON-LD snippets (generated-schema.json), but does not appear to have high-risk capabilities like arbitrary command execution or network exfiltration. - Sanitization: There are no explicit instructions for sanitizing or escaping the content retrieved from external URLs before processing.
Audit Metadata