strand-content-schema
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines structural requirements for MDX frontmatter (SEO titles, descriptions, slugs, etc.) and provides guidelines for validation using local tools.
- [COMMAND_EXECUTION]: The instructions direct the agent to use local CLI tools such as
strand validateandstrand-publish. These are standard development workflow commands within the context of the described CMS and do not show signs of malicious intent or privilege escalation. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process article content. While this creates an ingestion surface for potentially untrusted data, the skill mitigates risk by requiring the data to be formatted into a strict YAML schema and verified by a validation tool before publication. The severity is low as it encourages structured data boundaries.
Audit Metadata