seo-schema
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests data from HTML JSON-LD blocks, which represents an indirect prompt injection attack surface.\n
- Ingestion points: HTML source code is parsed to detect existing JSON-LD blocks (Workflow Step 1).\n
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard instructions that might be embedded within the detected JSON-LD data.\n
- Capability inventory: The skill involves local script execution (
scripts/validate-schema.ts) and generating structured data from templates.\n - Sanitization: No sanitization or filtering logic for the content of the parsed JSON-LD blocks is described in the skill metadata.\n- [COMMAND_EXECUTION]: The skill workflow includes running a local TypeScript script (
scripts/validate-schema.ts). This is used for validating schema markup against offline dumps and is a legitimate functional component of the skill's SEO-focused purpose.
Audit Metadata