world-crown

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands via a Bash tool to read specific markdown files from the world-code/ directory. This usage is restricted to hardcoded relative paths and is essential for the skill's primary function of information synthesis.
  • [PROMPT_INJECTION]: The skill processes data from external local files (voice.md, climax.md, etc.), which presents a surface for indirect prompt injection. However, it is used for legitimate content generation within a defined framework.
  • Ingestion points: Reads user-controlled content from world-code/voice.md, world-code/climax.md, world-code/method.md, and world-code/creation.md.
  • Boundary markers: No explicit delimiters or instructions are used to isolate the ingested content from the system prompt.
  • Capability inventory: The skill has read and write access to the filesystem via the Bash tool.
  • Sanitization: The skill does not implement specific sanitization or filtering for the content ingested from the markdown files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 09:28 PM