ask-matt

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a documentation-only router describing workflows for other skills. It does not contain any executable scripts, shell commands, or configuration that could be exploited.
  • [SAFE]: No instances of prompt injection, data exfiltration, or obfuscation were found. The skill uses natural language to describe process steps.
  • [SAFE]: The metadata includes 'disable-model-invocation: true', which is a security-positive configuration ensuring the model is not triggered during the display of this informational routing skill.
  • [SAFE]: The only external reference is an informational link to a developer education site (aihero.dev) regarding context window dictionary terms.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 12:21 PM
Security Audit — agent-trust-hub — ask-matt