storybook-story-writing
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill is designed to assist in creating or modifying component stories, which involves reading and writing to a local filesystem where untrusted content might exist.
- Ingestion points: The agent reads existing component files and project structures to generate stories (implied by the 'Read' and 'Glob' tools).
- Boundary markers: Absent. The skill does not instruct the agent to ignore or delimit potentially malicious comments or instructions found within the source code it processes.
- Capability inventory: The skill allows the use of
Bash,Write, andEdittools as defined in theSKILL.mdmetadata. - Sanitization: Absent. There is no logic provided to sanitize or validate the content of the components before they are processed by the agent.
Audit Metadata