200-agents-md

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to collect project metadata from the user and format it into a documentation file. This is a standard documentation task with no inherent security risk.
  • [COMMAND_EXECUTION]: While the skill references Java build commands such as ./mvnw clean verify, these are documented as strings within the resulting AGENTS.md file. There are no instructions to execute these or any other shell commands during the skill's operation.
  • [DATA_EXFILTRATION]: No network requests or sensitive file access patterns were found. The skill explicitly instructs contributors to avoid committing secrets, which aligns with security best practices.
  • [PROMPT_INJECTION]: The skill contains structural instructions (e.g., 'MANDATORY', 'CRITICAL') to ensure the agent follows a specific multi-step question-and-answer sequence. These are functional constraints for the interaction and do not represent attempts to bypass safety filters or extract system prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 06:08 AM