mfds-food-safety
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the agent to download the
@nomadamas/k-skillpackage from the npm registry usingnpx. This package is a vendor-owned resource. - [REMOTE_CODE_EXECUTION]: The use of
npxto execute commands from a remote package constitutes a remote code execution pattern. This is the intended mechanism for the vendor's ecosystem to provide up-to-date instructions and helper scripts. - [COMMAND_EXECUTION]: The skill provides specific shell commands using
npxfor the agent to execute in order to fetch instructions and run data lookup scripts. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points:
scripts/mfds_food_safety.pyretrieves records from external food safety APIs viak-skill-proxy.nomadamas.org. - Boundary markers: No explicit delimiters are used to separate external data from the agent's internal prompt context.
- Capability inventory: The skill is capable of shell command execution (
npx) and network requests (urllib.request). - Sanitization: The helper script includes a
summarize_textfunction that removes HTML tags and unescapes content, providing basic sanitization of the retrieved data.
Audit Metadata