repo2skill

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill contains internal testing and evaluation scripts, such as eval/run_eval.py and assets/test_scaffold_skill.py, which use subprocess.run to verify that generated skeletons pass the repository's quality gates. These executions are limited to local Python unit tests and shell-based validation tools provided within the repo.
  • [DATA_EXPOSURE]: The instructions in SKILL.md include a find command designed to help an agent locate the skill's base directory across common configuration paths (~/.claude, ~/.config, ~/.agents). This discovery is limited to locating the skill's own assets and does not target sensitive user files or credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 07:06 PM
Security Audit — agent-trust-hub — repo2skill