skills/kirkchen/beat/design/Gen Agent Trust Hub

design

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses git commands to stage and commit generated artifacts (git add and git commit). This is a standard part of the documented workflow for versioning changes.
  • [DATA_EXPOSURE]: The skill reads local project files including beat/config.yaml and .feature files to maintain context and ensure design consistency. These operations are restricted to the local workspace and do not target sensitive system directories.
  • [PROMPT_INJECTION]: The skill ingests data from local feature files and configuration to align new artifacts with existing styles. While this presents an inherent surface for indirect instruction injection from project files, the skill does not contain instructions that bypass safety filters or override agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 11:37 AM
Security Audit — agent-trust-hub — design