storyteller-pro
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data (premises, character details, genre, and tone) to generate stories and character profiles. This creates a surface for indirect prompt injection where a user could provide inputs designed to steer the agent's output behavior.
- Ingestion points: User input is collected during 'Step 1: รวบรวม context' (premise, genre, format, tone, setting, theme) in
SKILL.md. - Boundary markers: The skill does not implement explicit boundary markers or delimiters for user-provided data.
- Capability inventory: The skill instructs the agent to create and write to Markdown (
.md) files based on the generated content. - Sanitization: No specific sanitization or validation logic is defined for the user-supplied strings before they are incorporated into the creative process.
- [SAFE]: No evidence of data exfiltration, remote code execution, or credential exposure was found. The skill operates entirely within the creative writing domain using internal templates and example files provided in the package.
Audit Metadata