skills/withqwerty/nutmeg/nutmeg-store/Gen Agent Trust Hub

nutmeg-store

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to read a user-controlled profile file (.nutmeg.user.md) to tailor its data storage and publishing recommendations based on the user's goals and technical level. This creates a surface where malicious instructions inside the profile could influence the agent's behavior.
  • Ingestion points: The agent reads the .nutmeg.user.md file at the start of the interaction.
  • Boundary markers: There are no explicit delimiters or instructions to treat the file content as untrusted data.
  • Capability inventory: The skill is configured with powerful tools including Bash, Write, and Read capabilities.
  • Sanitization: No sanitization or validation logic is defined for the content retrieved from the user profile.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 03:24 PM
Security Audit — agent-trust-hub — nutmeg-store