book-ideation
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted user content which is then used to generate documents for a multi-step workflow.
- Ingestion points: The skill accepts raw ideas, brainstorm documents, and Zettelkasten research notes as input from the user (referenced in
SKILL.md). - Boundary markers: The instructions lack explicit boundary markers or directions for the agent to ignore instructions embedded within the user-provided content.
- Capability inventory: The skill instructions do not contain any shell commands, network operations, or sensitive file access patterns; it primarily uses a template (
assets/templates/book-concept-template.md) to structure output. - Sanitization: There is no logic provided to sanitize or validate the user-supplied input before it is incorporated into the Book Concept Document.
Audit Metadata