skills/brave/brave-core/pr/Gen Agent Trust Hub

pr

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh pr create) and standard git commands (git push) to automate the pull request process.- [COMMAND_EXECUTION]: The skill utilizes dynamic context injection (the !command syntax) in SKILL.md to run local git commands including git branch, git log, and git diff. These are standard read-only operations used to gather development context and do not involve the injection of external or untrusted arguments into the shell.- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes repository metadata that could be influenced by other contributors.
  • Ingestion points: Commit messages and branch names are retrieved from the local git history and loaded into the agent context via SKILL.md.
  • Boundary markers: No explicit delimiters or instructions are used to ensure the agent ignores potential instructions embedded within commit logs.
  • Capability inventory: The skill is capable of pushing code to remote servers and creating pull requests.
  • Sanitization: No sanitization is performed on the commit history before it is used to draft the pull request content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 06:15 PM