portfolio-story-architecture-by-13qd91c
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a legitimate design workflow focused on architectural synthesis from provided examples. It includes explicit safety guidelines that prohibit inventing sources, implying official endorsement, or making unauthorized account changes.- [EXTERNAL_DOWNLOADS]: The skill references external URLs in
references/cases.mdfor viewing images and videos hosted on well-known platforms (Twitter/X and GoodCase). These are provided as static visual references for the design workflow and do not involve the download or execution of scripts or binaries.- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to inspect external media using browser or image tools, which creates an ingestion point for external data. However, the instructions include specific attribution requirements and a 'Safety and attribution' section to prevent misuse of referenced content. - Ingestion points: External media links in
references/cases.md(e.g.,video.twimg.com,goodcase.ai). - Boundary markers: The skill lacks explicit 'ignore instructions' delimiters for external content but provides high-level safety constraints.
- Capability inventory: Requires the use of browser or image inspection tools to analyze visual traits.
- Sanitization: No explicit sanitization of external content is mentioned, though the workflow focuses on structural traits rather than content execution.
Audit Metadata