fragno-author
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use 'pnpm create fragno@latest' to scaffold new projects, which is a standard developer workflow for the Fragno framework.
- [EXTERNAL_DOWNLOADS]: The skill uses 'curl' to fetch documentation and search results from 'https://fragno.dev'. This domain is the official resource for the framework and is used to provide the agent with accurate implementation guidance.
- [REMOTE_CODE_EXECUTION]: Project initialization via 'pnpm create' involves downloading and running a scaffolding script from the vendor's official package registry.
- [PROMPT_INJECTION]: The process of fetching and reading external documentation via 'curl' creates an indirect prompt injection surface. 1. Ingestion points: Documentation URLs from 'https://fragno.dev' in 'SKILL.md'. 2. Boundary markers: Not specified in instructions. 3. Capability inventory: Shell command execution via 'pnpm' and file system access. 4. Sanitization: Not specified in instructions.
Audit Metadata