story

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill serves as a functional dispatcher for the worldwonderer writing suite, organizing user requests into appropriate categories like short stories, long-form novels, or technical setup tasks.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating user-provided text directly into prompts for downstream agents.
  • Ingestion points: The user query string is captured and passed directly into the agent spawn command in SKILL.md.
  • Capability inventory: The router dispatches tasks to skills with capabilities for file system initialization (/story-setup, /story-import) and browser automation (/browser-cdp).
  • Boundary markers: No delimiters or framing instructions are used to separate user data from the agent's internal prompt logic.
  • Sanitization: No explicit validation or escaping of user input is performed before it is used to trigger sub-skills or spawn agents.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 02:23 AM
Security Audit — agent-trust-hub — story