objection-destroyer

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [Prompt Injection] (SAFE): The instructions are limited to business logic for pitch generation. No instructions were found that attempt to override safety guidelines or reveal system prompts.
  • [Data Exposure & Exfiltration] (SAFE): The skill does not access local files, environment variables, or secrets. It has no network capabilities to exfiltrate data.
  • [Remote Code Execution] (SAFE): No remote scripts, package managers (npm/pip), or external URLs were detected for download or execution.
  • [Command Execution] (SAFE): The skill contains no shell commands, subprocess calls, or system interactions.
  • [Indirect Prompt Injection] (LOW): The skill accepts untrusted user input to generate pitches, creating a potential injection surface. However, the lack of dangerous capabilities (file/network/execution) makes this risk negligible. * Ingestion points: User responses provided via AskUserQuestion. * Boundary markers: Absent. * Capability inventory: No code, network, or file access tools. * Sanitization: No sanitization of user-provided business details is performed.
  • [No Code] (SAFE): The skill is entirely comprised of markdown instructions for the AI agent and does not ship with any scripts or executables.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 06:25 AM