worldview-game-horror-experience-rhythm
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, user-provided content such as game premises, scene lists, chapter outlines, and route descriptions. This data ingestion represents a surface for indirect prompt injection attacks where malicious instructions hidden in the data could attempt to override agent behavior.
- Ingestion points: According to SKILL.md and README.md, the agent requires external design materials, chapter outlines, and runtime evidence to generate the rhythm contract.
- Boundary markers: The instructions do not include specific delimiters or guidance for the agent to treat input data as untrusted or to ignore any embedded instructions within the user's design documents.
- Capability inventory: The skill is primarily focused on producing design documentation (Markdown and YAML) and coordinating with other internal design skills; no dangerous capabilities like shell execution, network exfiltration, or privileged file access were identified.
- Sanitization: The skill lacks explicit procedures for validating, sanitizing, or filtering the content of the ingested game design documents.
Audit Metadata