pr
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on executing local shell commands including
gitandgh(GitHub CLI) to manage branches, stage files, and interact with remote repositories. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from external sources to influence its logic and output.
- Ingestion points: The skill reads output from
git diff,git log, andgh issue list, as well as the content of.github/PULL_REQUEST_TEMPLATE.md. - Boundary markers: Absent. There are no delimiters or instructions to ignore instructions that might be embedded in the code diffs or issue descriptions being summarized.
- Capability inventory: The agent has the ability to execute git and gh commands via subprocesses, including pushing code to remote branches and creating pull requests.
- Sanitization: Absent. The skill encourages the agent to "analyze the diff to understand the changes" and "infer a branch name" directly from the content of the changes, which could be manipulated by an attacker who has contributed to the codebase.
Audit Metadata