Skills
skills/onsager-ai/dev-skills/issue-spec/Gen Agent Trust Hub

issue-spec

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a robust workflow for human-AI collaboration via GitHub issues, using standard markdown templates and references.
  • [COMMAND_EXECUTION]: The skill includes shell scripts (scripts/spec-list.sh and scripts/spec-show.sh) that leverage the GitHub CLI (gh) and jq to query repository metadata. These scripts are read-only and designed to provide a dashboard view of specification issues.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from GitHub issue bodies and titles. This data is used specifically for extracting progress indicators (e.g., plan checkboxes) and displaying status, presenting a minimal attack surface that is appropriate for its intended functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 10:41 PM
Security Audit — agent-trust-hub — issue-spec