Skills
Navigate
skills/microcmsio/skills/microcms-nextjs/Gen Agent Trust Hub

microcms-nextjs

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of external content from microCMS APIs, which represents a potential surface for indirect prompt injection if the source data is compromised. The instructions mitigate this by recommending robust input validation and secure architectural patterns.
  • Ingestion points: references/data-fetching.md and references/preview.md describe fetching content via the microcms-js-sdk.
  • Boundary markers: No specific delimiters for untrusted content are provided in the implementation examples, though the logic is confined to specific data types.
  • Capability inventory: Includes network operations via the SDK and route management (redirects) in Next.js.
  • Sanitization: The skill explicitly instructs users to validate IDs using regular expressions and use encodeURIComponent for redirects in references/preview.md and references/data-fetching.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 06:13 AM