designmd-supply-generator
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from arbitrary websites using the Context.dev web scraping API and interpolates it directly into an LLM prompt template. \n
- Ingestion points: Scraped content is stored in the
markdown.contentvariable and passed to thegenerateDesignMdFullfunction (SKILL.md). \n - Boundary markers: The prompt template lacks specific delimiters (e.g., XML tags or markdown blocks) or explicit instructions for the LLM to ignore instructions embedded within the scraped content. \n
- Capability inventory: The resulting output is returned to the user as a design document, which could contain malicious instructions for subsequent tasks. \n
- Sanitization: There is no evidence of filtering or escaping the external content before prompt interpolation. \n- [COMMAND_EXECUTION]: The installation and development guides include standard shell commands for the user to execute (
npm install,npm run dev,git clone). These are routine for development-oriented skills.
Audit Metadata