front-desk
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown and JSON configuration; no executable scripts, binaries, or active code components are present.
- [SAFE]: All referenced external services (e.g., GitHub, Cloudflare, Vercel) and organization-specific resources (e.g., satchmo.dev) are reputable and expected for this vendor.
- [COMMAND_EXECUTION]: The documentation mentions administrative commands for skill management, such as 'npx skills' and '/plugin install', which are part of the intended extension workflow.
- [PROMPT_INJECTION]: The skill functions as a router based on user input, creating a surface for indirect prompt injection. 1. Ingestion: Triggers in SKILL.md. 2. Boundaries: Absent. 3. Capability: Agent tool dispatch and plugin installation. 4. Sanitization: Absent. This risk is inherent to routing functionality and is mitigated by agent guardrails.
Audit Metadata