skills/matt-riley/mjrwtf/rpi-workflow/Gen Agent Trust Hub

rpi-workflow

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a legitimate development workflow designed to improve context management and task predictability in an interactive CLI environment.
  • [COMMAND_EXECUTION]: The skill references standard development commands such as make test, go build ./..., and make generate. These are executed within the context of the user's project (mjr.wtf) and are appropriate for the stated purpose of software verification.
  • [DATA_EXFILTRATION]: Artifact persistence is handled locally via a thoughts/ directory. The skill explicitly recommends excluding this directory from version control using .gitignore to prevent accidental exposure of local scratchpads. The mention of /share gist is a reference to a native GitHub Copilot CLI feature for intentional user-initiated sharing.
  • [PROMPT_INJECTION]: The prompt templates provided in the reference files are structured to guide the agent through specific engineering tasks (researching, planning, etc.) and do not contain instructions to bypass safety filters or override agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 09:16 AM