storyboard-prompts
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests multiple narrative and visual reference files which could theoretically contain malicious instructions.
- Ingestion points: Workflow step 1 reads files such as STORYBOARD_PIPELINE.md, dramaturgy rules, and reference manifests.
- Boundary markers: None identified; the skill instructions do not define delimiters for external data.
- Capability inventory: Capabilities are limited to writing JSONL and Markdown files to specific project subdirectories (03_preproduction, 04_generation). No shell execution, network access, or dynamic code evaluation is present.
- Sanitization: No sanitization or validation of input file content is described.
- [SAFE]: The skill frontmatter includes disable-model-invocation: true, which acts as a platform-level restriction. The workflow is entirely instructional and follows standard creative production practices without security-relevant side effects.
Audit Metadata