micro-steps-coach
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a set of instructional guidelines for an AI agent to act as a project management and technical coach. It does not contain executable code, automated scripts, or hidden commands.
- [SAFE]: All external references, such as the link to
eferro.net, are consistent with the stated authorship and serve as legitimate sources for the "Expand-Contract" architectural pattern. - [SAFE]: Code examples provided in
REFERENCE.mdare purely educational, demonstrating industry-standard safe migration strategies for databases and APIs. They are not intended for automatic execution by the agent. - [PROMPT_INJECTION]: No patterns indicative of system prompt overrides, safety filter bypasses, or jailbreak attempts were found.
- [DATA_EXFILTRATION]: The skill does not access sensitive local files or attempt to transmit data to unauthorized external domains. It utilizes standard agent tools (
Read,AskUserQuestion) for benign communication.
Audit Metadata