create-and-merge-pr
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could be used to influence the agent's behavior.
- Ingestion points: The skill reads issue titles, issue bodies, PR titles, PR bodies, and commit diffs from the GitHub repository (
SKILL.md). - Boundary markers: There are no explicit instructions or delimiters telling the agent to ignore instructions embedded within the issue or PR content.
- Capability inventory: The skill has the ability to execute
ghCLI commands (gh pr create,gh pr merge,gh issue close) andgitcommands (git push,git fetch,git checkout). - Sanitization: The skill follows safe practices by instructing the agent to pass text through structured arguments or safe shell quoting and writing multiline bodies to temporary files to prevent command injection at the shell level.
Audit Metadata