skills/pubx-ai/skills/raise-pr/Gen Agent Trust Hub

raise-pr

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes git and gh (GitHub CLI) to perform repository operations, including branch verification, fetching remote status, and creating pull requests. These are standard and expected behaviors for a development-focused tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the local repository, such as commit messages and code diffs, to automatically generate pull request metadata.
  • Ingestion points: Commit history (git log) and branch diffs are processed in SKILL.md to form the PR title and body.
  • Boundary markers: The skill explicitly recommends using a quoted heredoc ('EOF') when constructing the gh pr create command. This is a robust security measure that prevents the shell from interpreting or expanding any potentially malicious content contained within the PR body text.
  • Capability inventory: The skill has the ability to interact with the GitHub API via the gh command-line tool and execute git commands.
  • Sanitization: Structural sanitization is achieved through the use of the quoted heredoc in the provided command template, ensuring that the PR body content is treated as a literal string by the shell.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 11:21 PM