skills/yonatangross/orchestkit/cover/Gen Agent Trust Hub

cover

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows secure development practices by explicitly instructing agents to only modify test files and never modify production source code during the failure healing loop.
  • [SAFE]: The skill uses structured subagent prompts to generate code and maintains its internal state within the local .claude directory, ensuring workflow isolation and continuity.
  • [COMMAND_EXECUTION]: The skill uses CronCreate to schedule recurring test coverage checks. This automated execution is used for the legitimate purpose of monitoring coverage drift over time.
  • [PROMPT_INJECTION]: The skill interpolates user-provided scope arguments into subagent prompts. While this creates a potential indirect prompt injection surface, the risk is mitigated by the skill's specific focus on testing patterns (AAA, Page Object Model) and its primary purpose of developer automation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 11:09 AM