lov-better-github-desc

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a robust security model for managing local configurations. The scripts/profile_store.py utility strictly enforces a policy of not storing sensitive information such as tokens, passwords, or API keys in the persistent profile records.
  • [SAFE]: Clear execution boundaries are defined in SKILL.md. The workflow enforces a separation between read-only analysis/preview and actual modification of the GitHub repository. It requires explicit user authorization before performing any gh repo edit operations, preventing accidental or unauthorized changes.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local README.md and package.json files to generate repository descriptions. While this creates a theoretical surface for indirect prompt injection, the risk is mitigated by the workflow's specific instructions to summarize content, ignore marketing exaggeration, and filter out installation commands and badges. The mandatory preview step ensures that users can review the generated output before it is committed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 09:42 AM
Security Audit — agent-trust-hub — lov-better-github-desc