ship
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a series of shell commands using
gitandgh(GitHub CLI) to analyze repository churn, check for whitespace errors, commit review fixes, and push changes to remote branches. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository's history (git logs) and diffs to generate PR summaries. While this represents an attack surface for indirect prompt injection, the skill mitigates shell injection risks by using a literal HEREDOC (
<<'EOF') when writing the PR body to a temporary file. - [DATA_EXPOSURE]: The skill reads project metadata such as git remote URLs and manages local readiness state in the user's home directory (
~/.config/steveos/readiness). These operations are scoped to the skill's primary purpose of tracking PR pipeline progress.
Audit Metadata