skills/jekudy/grillme-skill/grillme/Gen Agent Trust Hub

grillme

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely composed of natural language instructions and structural templates for interactive interviewing. It does not include any scripts, shell commands, or external dependencies.
  • [SAFE]: No network operations or data exfiltration patterns were detected. The skill uses the standard AskUserQuestion tool for interaction within the platform's safe execution environment.
  • [SAFE]: No obfuscation, prompt injection, or persistence mechanisms are present. The metadata matches the instructional content and intended purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and summarize user input during interviews. While this provides a surface for indirect prompt injection (where a user might try to influence the agent's behavior through their answers), the skill lacks any dangerous capabilities like network access or file-system writes that could be exploited. The primary behavior is focused on questioning and summarization, which falls within standard AI interaction safety boundaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 08:46 AM
Security Audit — agent-trust-hub — grillme