create-design-md
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use standard shell utilities such as grep, find, and ls to inspect target codebases for design tokens and styling configurations, as specified in 'references/extraction-cheatsheet.md'.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its core function involves ingesting untrusted data from URLs and source code. 1. Ingestion points: 'SKILL.md' describes processing data from live URLs, repositories, and HTML snapshots. 2. Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the source data. 3. Capability inventory: The skill is capable of executing shell commands and performing browser navigation. 4. Sanitization: No explicit content sanitization or escaping mechanisms are mentioned for the extracted data.
Audit Metadata