master-plan-manager

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves reading and updating the MASTER_PLAN.md file. Although processing content from external files can expose an agent to indirect prompt injection, this skill incorporates defensive strategies such as a 'Read First' requirement, structure preservation, and a validation checklist to verify the integrity of updates.
  • [COMMAND_EXECUTION]: The skill provides examples of standard shell commands for error recovery, such as cp and git checkout. These are documented as legitimate local operations for file restoration and do not involve remote code execution or unauthorized privilege escalation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 01:39 PM