skills/citypaul/.dotfiles/wtf/Gen Agent Trust Hub

wtf

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely instructional and restricted to text processing. The 'disable-model-invocation' flag is set to true in the frontmatter, preventing the agent from calling any tools or performing actions beyond the re-explanation task.
  • [DATA_EXFILTRATION]: The skill instructs the agent to read specific local documentation files (e.g., GLOSSARY.md, CONTEXT.md, *.glossary.yml) to verify terminology. These are standard repository-read operations for technical accuracy and are not associated with any network exfiltration path.
  • [EXTERNAL_DOWNLOADS]: References to source code on GitHub (mintuz/skills) are provided for attribution and licensing purposes. These are static URL references and do not represent runtime code downloads or execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 03:06 PM
Security Audit — agent-trust-hub — wtf