skills/alpoxdev/hypercore/git-maker/Gen Agent Trust Hub

git-maker

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill includes explicit security guidelines in rules/commit-and-push-policy.md and SKILL.md to prevent the accidental inclusion of secrets and credentials in commits.
  • [SAFE]: The scripts/git-maker-fast.sh script implements safety checks that block force-pushing to protected branches (main, master) and prevent operations from a detached HEAD state.
  • [SAFE]: Command execution is limited to standard git operations and local scripts. No unauthorized external network calls or remote code execution patterns were identified.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from git diffs and file names, creating a surface for Indirect Prompt Injection. 1. Ingestion points: scripts/git-maker-fast.sh (git status/file lists). 2. Boundary markers: Present in rules/agent-parallelism.md templates. 3. Capability inventory: scripts/git-maker-fast.sh (git push). 4. Sanitization: Absent, relies on instruction-based boundaries.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 03:26 PM