swiggy-mcp-instamart

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration techniques were detected. The skill follows established e-commerce security practices by requiring explicit human confirmation before placing orders and providing clear instructions for multi-store checkout scenarios.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect injection as it processes data from external product searches and store listings.
  • Ingestion points: Data returned by the search_products, your_go_to_items, and get_cart tools in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters to separate untrusted API data from agent instructions.
  • Capability inventory: The agent can perform sensitive actions such as update_cart, create_address, and checkout.
  • Sanitization: No explicit sanitization or validation logic is defined for the content returned by the Swiggy API tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 10:16 AM
Security Audit — agent-trust-hub — swiggy-mcp-instamart