skills/sarthib7/agentsmith/grill-me/Gen Agent Trust Hub

grill-me

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill does not contain any malicious instructions, obfuscation, or unauthorized data access patterns. Its primary function is to provide a logic-based framework for design review.
  • [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection as it processes user-provided plans which are untrusted data.
  • Ingestion points: User-provided designs and plans supplied during the session.
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore directives potentially embedded in the user's plan.
  • Capability inventory: The agent is directed to use codebase exploration tools to answer questions.
  • Sanitization: No specific sanitization or validation logic is defined for the content of the plan being analyzed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 11:04 AM
Security Audit — agent-trust-hub — grill-me