skills/dungsil/skills/vibe-init/Gen Agent Trust Hub

vibe-init

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests data from local repository files, including AGENTS.md, CONTEXT.md, and ADR directories, to determine the project's configuration state. These files serve as ingestion points for untrusted data, creating an indirect prompt injection surface. The skill provides mitigation by presenting its findings and proposed file edits to the user for approval before writing changes to the filesystem.
  • [COMMAND_EXECUTION]: The skill executes git remote -v to identify the repository's origin. It also provides instructions for using standard command-line interfaces such as gh (GitHub CLI) and glab (GitLab CLI) for issue management, which are established developer tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 04:52 PM