awesome-design-md-jp
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs users to clone a repository from GitHub (
github.com/kzhrknt/awesome-design-md-jp) and references external visual resources atkzhrknt.github.io. It also links to documentation from well-known sources like Google, W3C, and Microsoft.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructs the AI agent to adopt and follow instructions found in externalDESIGN.mdfiles, creating a potential vector for indirect prompt injection if the files are modified to include malicious directives.\n - Ingestion points:
DESIGN.mdfiles sourced from the external repository and added to the agent's context.\n - Boundary markers: Absent; the agent is instructed to follow the design specifications directly without delimiter-based safety warnings.\n
- Capability inventory: The agent environment usually provides file system operations and shell command execution.\n
- Sanitization: Absent; the skill does not include validation or filtering for the external markdown specifications.
Audit Metadata