story-bible
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text (draft chapters, outlines, and notes) to extract story facts. This represents an indirect prompt injection surface where a user-provided document could contain instructions intended to influence the agent's behavior.
- Ingestion points: User-provided material (drafts, notes, outlines) described in the 'What to ask for' section.
- Boundary markers: None explicitly defined in the skill instructions to separate user content from system instructions.
- Capability inventory: The skill mentions the ability to call a 'notes tool' or 'Scratchpad connector' to save results, which involves writing data to an external application.
- Sanitization: No explicit sanitization or filtering of the processed text is mentioned.
- [SAFE]: The skill references a 'Scratchpad connector' for saving notes. This is a vendor-owned resource associated with the skill's author ('scratchpad-sh') and represents standard functionality for this specific tool.
Audit Metadata