seo-schema-jsonld
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Node.js script (
validate-jsonld.mjs) via theBashtool to perform validation checks. The commandnode ${CLAUDE_SKILL_DIR}/../../scripts/validate-jsonld.mjs --url <u>involves executing internal logic provided with the skill context. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) as it processes untrusted data from web pages:
- Ingestion points: The skill ingests
rendered_domandraw_htmlfrom external web pages provided as input (SKILL.md). - Boundary markers: There are no explicitly defined delimiters or instructions to ignore embedded commands within the ingested HTML content to prevent adversarial influence.
- Capability inventory: The skill can execute shell commands through the
Bashtool and retrieve external data viaWebFetch(SKILL.md). - Sanitization: No explicit sanitization, validation, or filtering of the ingested HTML/DOM content is described before the data is processed by the agent.
Audit Metadata