gh-enrich-pr-description

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes git and gh (GitHub CLI) commands to analyze branch changes, retrieve commit history, and manage pull requests. These are standard operations for repository management tasks.
  • [DATA_EXFILTRATION]: The skill accesses commit metadata, including author names and email addresses, via git log commands. This data is used locally within the agent session to identify contributors for CC mentions in the PR description and is not transmitted to unauthorized external domains.
  • [PROMPT_INJECTION]: The skill processes data from external sources, such as commit messages and existing pull request descriptions, creating a surface for indirect prompt injection.
  • Ingestion points: Commit messages retrieved via git log and PR metadata retrieved via gh pr view in SKILL.md.
  • Boundary markers: Absent; the workflow does not implement specific delimiters or instructions to ignore embedded instructions in the ingested data.
  • Capability inventory: The skill can read repository history via git and update PR content via gh pr edit.
  • Sanitization: Absent; the skill provides the raw metadata to the agent for synthesis into the final description without explicit filtering or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 12:53 PM