weekly-retro

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses standard command-line tools (git, gh) to gather data from local repositories and GitHub issues. These operations are consistent with the skill's stated purpose of project management and retrospective analysis.
  • [SAFE]: Data integrity is prioritized through 'Iron Rules' that mandate verification before creating issues and cross-checking verbal information against canonical source files. This mitigates risks associated with data fabrication or hallucination.
  • [SAFE]: The skill performs local file operations (reading/writing logs and configuration) within the project directory. There are no network requests to untrusted or external domains; all external interactions are mediated through the official GitHub CLI tool.
  • [SAFE]: Prompt instructions are focused entirely on the business logic of retrospectives and do not contain attempts to bypass AI safety guidelines or override system constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 05:04 PM
Security Audit — agent-trust-hub — weekly-retro