swiggy-dineout-booking

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines a workflow for the agent to use the swiggy CLI tool for searching restaurants, viewing details, and managing table bookings.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied data such as restaurant names, IDs, and reservation dates, which are interpolated into CLI command arguments. This presents a potential surface for indirect prompt injection or command injection. (1) Ingestion points: User-provided search queries, restaurant IDs, and reservation dates in SKILL.md. (2) Boundary markers: Search queries are wrapped in double quotes in example commands. (3) Capability inventory: Subprocess execution of the swiggy CLI tool. (4) Sanitization: No explicit sanitization or input validation logic is described in the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 03:22 PM