skill-tester

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Bash script (scripts/run-tests.sh) to automate validation tasks across the repository.
  • [COMMAND_EXECUTION]: The validation script invokes python3 to run a local utility script (.claude/skills/skill-creator/scripts/quick_validate.py) for checking Anthropic skill specifications.
  • [COMMAND_EXECUTION]: Performs syntax validation on Bash scripts using bash -n, which checks for errors without executing the script content.
  • [SAFE]: The skill's operations are limited to reading repository files (e.g., SKILL.md, CLAUDE.md, AGENTS.md) and checking metadata like line counts and file permissions.
  • [SAFE]: No network operations, credential access, or attempts to bypass agent safety guidelines were detected. The skill's behavior matches its stated purpose as a quality assurance tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 06:59 AM
Security Audit — agent-trust-hub — skill-tester