merge
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs legitimate repository maintenance tasks using established local CLI tools. All operations are confined to the local repository environment and require explicit user confirmation for the core merge action.
- [COMMAND_EXECUTION]: The skill executes
gitandgh(GitHub CLI) commands to automate the pull request lifecycle, including branch status checks, CI monitoring, and merging. These operations are performed in response to user requests and are consistent with the skill's stated purpose. - [INDIRECT_PROMPT_INJECTION]: The skill processes repository-specific instruction files (such as
AGENTS.mdandCLAUDE.md) and GitHub pull request metadata to determine merge procedures. While this represents an ingestion point for external data, the skill uses this information appropriately to identify project-specific rules and CI requirements. - Ingestion points: Reads
AGENTS.md,CLAUDE.md, and PR metadata viagh pr view. - Boundary markers: None explicitly defined for these configuration files.
- Capability inventory: The skill has capabilities to manage branches and execute merges via
gitandgh. - Sanitization: None explicitly defined for the content of these documentation files.
Audit Metadata