schema-markup-generator

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns such as credential theft, privilege escalation, or persistence mechanisms were detected. The skill is focused on generating static JSON-LD markup templates.\n- [PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection due to its feature that extracts content from external websites.\n
  • Ingestion points: Data is ingested via a web crawler that extracts content from third-party URLs provided by the user, as described in SKILL.md.\n
  • Boundary markers: The instructions do not specify delimiters or constraints for the agent to differentiate between system instructions and crawled data.\n
  • Capability inventory: The agent is tasked with formatting external content into valid JSON-LD code and providing SERP previews.\n
  • Sanitization: There are no instructions for sanitizing or filtering input from crawled pages before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 07:24 AM