claude-design-system-prompt
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires cloning an external repository from GitHub:
https://github.com/Trystan-SA/claude-design-system-prompt.git. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, such as extracting design systems from arbitrary URLs (e.g.,
stripe.com) or analyzing codebases for components. This creates a surface for indirect prompt injection attacks where malicious instructions hidden in the processed data could influence the agent's behavior. - Ingestion points: External URLs, website content, and local source code files mentioned in triggers and examples (e.g.,
SKILL.md). - Boundary markers: The skill documentation does not specify the use of delimiters or specific instructions to the agent to ignore directives embedded within the ingested data.
- Capability inventory: The skill documentation demonstrates the use of file system reads (
Path().read_text(),readFileSync) and network-based LLM API calls (client.messages.create). - Sanitization: No evidence of input sanitization or filtering is present in the skill instructions or examples.
Audit Metadata