new-skill
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute several local Python scripts and shell scripts for scaffolding (e.g.,
new-skill.py), linting (e.g.,swh-lint.py), and verification (e.g.,check.sh). These operations are consistent with its primary purpose as a developer tool for skill creation. - [NO_CODE]: The skill itself contains only Markdown instructions and does not bundle its own scripts, instead referencing external scripts expected to be present in the user's local environment (~/.claude/harness).
Audit Metadata