anylist

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill translates user requests into shell commands using the anylist CLI to interact with the AnyList shopping list service.
  • [EXTERNAL_DOWNLOADS]: The skill relies on the anylist-cli package, which it instructs the user to install from the npm registry.
  • [PROMPT_INJECTION]: The skill processes user-supplied input (such as item names and list names) and interpolates it into shell commands. This creates a surface for indirect command injection if input is not properly handled.
  • Ingestion points: User-provided list names and grocery items described in SKILL.md.
  • Boundary markers: The skill instructions provide examples using double quotes around arguments (e.g., anylist add "Grocery" "Milk") to encapsulate user data.
  • Capability inventory: Execution of anylist CLI commands through the system shell.
  • Sanitization: No explicit sanitization or escaping rules are defined within the skill text; it relies on the agent's default behavior for command construction.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 12:24 AM