story-splitting
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied story text, which creates a theoretical surface for indirect prompt injection if the input contains malicious instructions.
- Ingestion points: The user story provided in the initial argument or Phase 1 setup.
- Boundary markers: The skill employs a structured phase-based workflow, though it lacks explicit delimiters to distinguish untrusted user text from system instructions.
- Capability inventory: The skill is capable of writing documentation files to the local file system and generating Mermaid diagrams.
- Sanitization: There is no explicit sanitization or validation of the input text mentioned in the instructions.
Audit Metadata