script-writer
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external brand profiles and video idea objects to generate production scripts.
- Ingestion points: Processes data from
shortform-idea-engine/references/brand-profile-template.md,01-decodes/[video_id].md, and user-supplied brand profiles provided during the input stage. - Capability inventory: The skill's operations are limited to reading local files and generating markdown text; it does not invoke tools for network access, shell command execution, or system modification.
- Boundary markers: The instructions do not specify the use of clear delimiters or boundary markers to isolate untrusted user data from the core agent instructions.
- Sanitization: There is no explicit logic defined to sanitize, escape, or validate the content of the brand profiles or idea objects before they are interpolated into the script generation process.
Audit Metadata