NYC

search-for-service

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (HIGH): The skill uses 'npx awal@latest' to download and run code from the npm registry. The package is not from a trusted organization, and use of '@latest' permits unreviewed code changes to execute.
  • REMOTE_CODE_EXECUTION (HIGH): Using 'npx' on an unverified third-party package allows for arbitrary remote code execution on the host system.
  • COMMAND_EXECUTION (MEDIUM): The skill requires Bash tool access to execute the discovery and inspection commands.
  • PROMPT_INJECTION (LOW): This skill contains an indirect prompt injection surface where untrusted data could influence agent behavior. (1) Ingestion points: Data from bazaar search results and endpoint details in 'SKILL.md'. (2) Boundary markers: Absent. (3) Capability inventory: Bash execution via npx. (4) Sanitization: Absent.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 04:37 PM