scripting-and-storyboarding
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from other internal skills such as 'idea-generation-and-ideation' and 'short-form-video-script'. This creates a theoretical surface for indirect prompt injection if the source data contains malicious instructions. However, the skill's lack of executable tools and its explicit instructions to reject deceptive content mitigate this risk.
- Ingestion points: The skill is designed to read input from 'idea-generation-and-ideation', 'short-form-video-script', 'brand-profile', and 'design-and-templates' as specified in SKILL.md.
- Boundary markers: None explicitly defined in the prompt interpolation logic.
- Capability inventory: The skill generates text-based planning artifacts (AV scripts, shot lists, storyboards) and does not possess capabilities for file modification, network requests, or shell execution.
- Sanitization: No programmatic sanitization; instead, it uses ethical constraints and an 'honesty pass' to refuse staged-as-candid content or script plagiarism.
Audit Metadata