ship-it
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a routine development workflow using git and the GitHub CLI (gh). No malicious patterns such as credential theft, remote code execution from untrusted sources, or persistence mechanisms were found.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided content (like PR descriptions and commit messages) which is a potential surface for indirect prompt injection. However, it implements strong sanitization by using quoted heredocs (<<'EOF') in its shell commands, ensuring that the input is treated as literal text and not interpreted as executable shell code.
- Ingestion points: User-defined text for commits, PRs, and comments in SKILL.md.
- Boundary markers: EOF delimiters are used for multi-line strings.
- Capability inventory: Execution of git and gh CLI tools.
- Sanitization: Quoting the heredoc delimiter ('EOF') prevents variable expansion and command substitution within the text blocks.
Audit Metadata