worldview-game-horror-production
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided creative briefs to drive a multi-phase production workflow that results in software artifacts.
- Ingestion points: The skill accepts a creative brief containing premise, protagonist, and desired story facts in
SKILL.md(Section 1). - Boundary markers: There are no explicit instructions for the agent to use boundary markers or delimiters to isolate user-supplied creative text from the generation of production logic.
- Capability inventory: The skill possesses the capability to generate a "runnable build," "project boot," "test harness," and perform "deployment" in
SKILL.md(Section 11). - Sanitization: The instructions do not define sanitization or validation routines for the user's brief before it is used to influence the implementation of the game's logic and scripts.
- [DYNAMIC_EXECUTION]: The skill's primary function involves the dynamic assembly and implementation of software builds based on abstract design requirements.
- Evidence:
SKILL.md(Section 11) guides the agent through implementing vertical slices, including establishing project boot and deployment. This represents the generation and execution of code strings and build processes triggered by the design parameters.
Audit Metadata