reply-to-pr-threads
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
gh api graphqlto interact with the GitHub API. This usage is transparent and directly related to its stated purpose of managing pull request threads. - [DATA_EXFILTRATION]: All network operations are directed towards GitHub's official GraphQL API. The skill does not access sensitive local files or transmit data to unauthorized external domains.
- [PROMPT_INJECTION]: The skill instructions contain clear logic for drafting replies and do not include patterns designed to bypass agent safety filters or override system instructions.
- [PROMPT_INJECTION]: While the skill processes external data (PR comments) which could theoretically contain indirect injection, the inclusion of a human-in-the-loop confirmation step (
AskUserQuestion) before posting effectively mitigates the risk of unauthorized actions.
Audit Metadata