ln-221-story-creator

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted input to generate content for external platforms, creating a surface for indirect prompt injection.
  • Ingestion points: Data enters the workflow via epicData, idealPlan, newStoryDescription, and standardsResearch.
  • Boundary markers: The instructions do not define delimiters or explicit directions to the agent to ignore instructions embedded within the input variables.
  • Capability inventory: The skill utilizes tool access to create stories in Linear, update kanban boards, and write summary artifacts to user-provided file paths.
  • Sanitization: There is no evidence of text sanitization or escaping of input data before it is incorporated into generated documents.
  • [SAFE]: The skill defines a legitimate administrative automation workflow for software development, focusing on enforcing quality standards such as INVEST validation and template consistency.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 01:53 AM