snap-forge
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs legitimate software development tasks, such as managing git branches and worktrees. Its use of the
~/.worktreesdirectory is a standard practice for git worktree management. - [SAFE]: Command execution is limited to running local project tests, linters, and formatters. These are expected behaviors for a TDD automation skill and are controlled by the project's own configuration files (e.g.,
package.json,Cargo.toml). - [SAFE]: The skill accesses GitHub issues to gather context for TDD cycles. While this constitutes an indirect prompt injection surface, it is a functional requirement for the skill's purpose and does not involve data exfiltration or unauthorized access.
- Ingestion points: GitHub issue comments are ingested via
gh issue viewas described inSKILL.md(§1 Orient). - Boundary markers: The instructions do not define specific boundary markers for external data.
- Capability inventory: The skill can execute git commands and project-specific test/lint scripts through the shell as described in
SKILL.md(§3, §4, and §5). - Sanitization: No explicit sanitization or filtering of GitHub comment content is mentioned.
Audit Metadata