travel-city-walk-by-1wr1qau
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a structural guide for generating AI video prompts based on existing 'GoodCase' examples. It restricts its context to internal reference files (
references/cases.md) and user-provided inputs. - [SAFE]: It contains explicit safety and attribution instructions, preventing the agent from inventing sources, impersonating creators, or making external changes without approval.
- [DATA_EXPOSURE]: The skill references external URLs for video and image examples (e.g.,
goodcase.ai,media.goodcase.ai,x.com). These are well-known or niche-relevant services related to the skill's primary purpose of visual analysis and do not involve sensitive data exfiltration. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data for subject and brand replacement. However, it implements a 'reference contract' (Preserve/Replace/Avoid) which acts as a boundary for how that data is used, and the impact is limited to the generation of a motion brief/prompt artifact.
Audit Metadata