NYC

launch-readiness-auditor

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill processes untrusted external data (codebase files) and lacks boundary markers to prevent embedded instructions from influencing the agent's behavior. * Ingestion points: Processes README, CLAUDE.md, and source files via Read, Glob, and Grep. * Boundary markers: Absent. * Capability inventory: Includes Bash (run tests) and WebFetch (check URLs). * Sanitization: Absent.
  • [Command Execution] (SAFE): The skill includes the Bash tool to run tests and check builds. This is a legitimate utility for a code auditor and does not appear to be used maliciously in the provided instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:15 PM