kuroco-content-management

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFE
Full Analysis
  • [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or sensitive local file access detected. API interactions use relative paths and standard authentication patterns (credentials: 'include').
  • [Unverifiable Dependencies & Remote Code Execution] (SAFE): No external package dependencies or remote script execution patterns were found in the skill files.
  • [Indirect Prompt Injection] (LOW):
  • Ingestion points: Content is retrieved from the Kuroco CMS API (e.g., 'subject', 'contents') in files SKILL.md and references/filter-query.md.
  • Boundary markers: No delimiters or instructions to ignore embedded commands are present in the provided templates.
  • Capability inventory: The skill defines patterns for creating, updating, and deleting content via the CMS API.
  • Sanitization: The code snippets demonstrate direct interpolation of search keywords into filter strings without explicit sanitization, which is a common pattern for this API but represents a potential injection surface if the agent handles malicious CMS content.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 07:48 PM