story-design
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input during the story creation workflow and processes it to generate files, which could lead to unintended behavior if the user provides malicious instructions disguised as a story idea.
- Ingestion points: The user's original story idea is collected in Step 2 ('Ask for Original Thought') of the workflow in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or protective framing to distinguish between user-provided story content and agent instructions during the generation phases (Step 4 and Step 6).
- Capability inventory: The skill has the capability to write markdown files to the
story_specs/directory (Step 6). - Sanitization: There is no explicit validation or sanitization step to filter instructions out of the user's provided creative input.
Audit Metadata