kuroco-content-structure

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill designs and creates content definitions based on user requirements and existing site metadata.
  • Ingestion points: User instructions regarding content models and outputs from administrative tools like whoami, topics_group-get, and group-list (SKILL.md).
  • Boundary markers: The skill uses a structured design template but does not explicitly define delimiters for untrusted user input within the final tool payloads.
  • Capability inventory: Uses write-capable tools including topics_group-create, topics_group-update, csvtable-create, and tag-create to modify CMS configurations.
  • Sanitization: There are no explicit instructions to sanitize or validate user-provided strings such as field names, slugs, or descriptions before they are interpolated into the MCP tool arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 07:36 AM
Security Audit — agent-trust-hub — kuroco-content-structure