reason-grill-core

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains only instructional markdown and lacks any code, shell commands, network access, or external dependencies.
  • [PROMPT_INJECTION]: While the skill contains phrases like 'ignore your instructions', these are used defensively in the 'Untrusted Input Warning' section to advise the agent against obeying directives embedded within analyzed content, which is a best practice for maintaining agent safety.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 09:44 AM
Security Audit — agent-trust-hub — reason-grill-core