story-idea-generator
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to perform file system operations to ensure output persistence. This includes checking for and updating project-specific configuration files (e.g.,
context/output-config.mdor.story-idea-generator-output.md) and writing generated story ideas to new markdown files using the pattern{concept-name}-{date}.md. These operations are consistent with the skill's stated purpose of maintaining a history of generated creative work. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied story ideas and genre preferences, creating an ingestion surface for untrusted data.
- Ingestion points: User-provided text for story hooks, character ideas, and genre preferences during the brainstorming interaction.
- Boundary markers: The instructions provide a structured five-phase process and modular framework to categorize input, but they do not define explicit delimiters or "ignore" instructions for the processed user content.
- Capability inventory: The agent is granted the capability to write and modify local files (SKILL.md).
- Sanitization: There are no instructions for sanitizing or escaping the user's input before it is used to generate or save content, though the generative nature of the task (story writing) significantly limits the impact of potential injection.
Audit Metadata