storyboard-manager
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes local Python scripts (
timeline_tracker.py,consistency_checker.py) to perform story analysis tasks. It also uses thegreputility to search through bundled reference documentation. These commands are executed within the local project scope to support character and plot development. - [INDIRECT_PROMPT_INJECTION]: The skill analyzes user-provided markdown files such as character profiles and chapter drafts. This presents a surface for processing external data, but the provided scripts use regular expression matching for extraction rather than executing content as code.
- Ingestion points: Files located in the
characters/,chapters/, andstory-planning/directories. - Boundary markers: The skill relies on specific folder structures and Markdown headers to delineate content, though it lacks explicit "ignore instructions" delimiters for user content.
- Capability inventory: Local file system read access and execution of bundled scripts via the Python interpreter.
- Sanitization: User-provided text from story files is processed via regex for timeline and consistency markers and is not used to dynamically construct shell commands or executable code.
Audit Metadata