sd-script-engine
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied stories and scripts, creating an attack surface for indirect prompt injection.
- Ingestion points: User narratives and external scripts enter the agent context via the registration process defined in references/source-registration.md.
- Boundary markers: The skill does not employ explicit boundary markers or delimiters to isolate untrusted data within the prompts, relying instead on internal fact-labeling logic.
- Capability inventory: The skill performs extensive file-writing operations across multiple project stages as documented in references/six-stage-pipeline.md and references/roundtable-review.md.
- Sanitization: There are no instructions for sanitizing or escaping the interpolated user content to prevent instruction override.
Audit Metadata