skills/rolemodel/skills/create-pr/Gen Agent Trust Hub

create-pr

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes Bash commands via Git and the GitHub CLI (gh) to manage repository state and interact with remote pull requests.
  • [DATA_EXFILTRATION]: The skill captures user interface screenshots and recordings for inclusion in pull requests, which are uploaded to GitHub. It explicitly instructs the agent to omit credentials or customer data and requires visual verification of the images before they are attached.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from Git logs, diffs, repository templates, and external ticket trackers (Jira, Linear) to generate PR descriptions.
  • Ingestion points: External data is retrieved from Git logs, Git diffs, gh pr view, repository templates, and ticket tracker APIs.
  • Boundary markers: The instructions do not define specific delimiters for separating external data from agent instructions.
  • Capability inventory: The skill has the capability to execute git commit, git push, gh pr create, and gh pr edit.
  • Sanitization: While no automated sanitization is described, the skill enforces a mandatory human confirmation step before any permanent actions (committing, pushing, or creating/editing PRs) are executed.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 06:49 PM