merging-stacked-prs
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes various GitHub CLI commands (
gh) to manage pull requests. These commands are essential to the skill's primary function and are implemented using structured JSON output (--json) to prevent common parsing vulnerabilities. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub (pull request metadata and author information). To mitigate injection risks, the skill uses official API schemas via GraphQL and JSON, avoiding the processing of raw, unstructured text. It also mandates a verification step if pull request authors do not match, preventing unauthorized stacking operations.
- [DATA_EXPOSURE_EXFILTRATION]: While the skill accesses repository metadata, it does not access sensitive local files (such as SSH keys or environment secrets) and restricts its operations to the official GitHub API and the local working directory.
Audit Metadata