ship-it
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill dynamically identifies and executes shell commands defined in repository configuration files such as
package.json,CLAUDE.md,AGENTS.md, and ecosystem-specific files (e.g.,Cargo.toml,go.mod). This is used to run project-specific quality gates and tests. - [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks due to its reliance on untrusted external data.
- Ingestion points: The skill reads repository-local instruction files (
CLAUDE.md,AGENTS.md) and fetches external GitHub PR comments and review threads to determine necessary fixes. - Boundary markers: There are no explicit boundary markers or delimiters defined to separate instructions found in PR comments or local config files from the core skill logic.
- Capability inventory: The agent has the capability to execute shell commands, perform git operations (commit, push, merge), and interact with the GitHub API via
ghCLI. - Sanitization: The skill does not implement sanitization or validation of the content retrieved from GitHub comments or project-local instruction files before acting upon them.
Audit Metadata