skills/atpaawej/founderkit/narrative/Gen Agent Trust Hub

narrative

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is strictly instructional and does not perform any command execution, subprocess spawning, or system-level modifications.
  • [SAFE]: Data operations are confined to reading and writing within the skill's local memory/ directory for narrative persistence, avoiding exposure of sensitive system files.
  • [SAFE]: The configuration explicitly includes security-conscious settings, such as disable-model-invocation: true, which restricts the execution environment.
  • [SAFE]: No obfuscation, prompt injection, or remote data exfiltration patterns were detected in the instructions or metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 05:02 PM
Security Audit — agent-trust-hub — narrative