merging-dependabot-prs
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) andgitto manage pull requests. It follows security best practices by using argument arrays instead of shell strings (via Node.jsspawnSync), terminating option lists with--to prevent flag injection, and strictly validating all external identifiers (pull request numbers, commit SHAs, package names, and tags) against restrictive regular expressions before use. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from pull request titles, bodies, and release notes. This risk is effectively mitigated by explicit instructions to treat this data as untrusted, the use of hardcoded strings for bot commands (e.g.,
@dependabot rebase), and a mandatory human-in-the-loop approval step for the generated plan before any actions are executed.
Audit Metadata