Skills
Navigate
skills/drvoss/everything-copilot-cli/github-pr-workflow/Gen Agent Trust Hub

github-pr-workflow

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from GitHub pull requests (comments, descriptions, and diffs). Malicious instructions embedded in these fields could influence the agent's behavior during automated tasks.
  • Ingestion points: Processes PR content via github-mcp-server-pull_request_read and list_pull_requests in SKILL.md.
  • Boundary markers: No explicit instructions are provided to the agent to treat the PR content as untrusted or to disregard embedded commands.
  • Capability inventory: The skill utilizes gh api graphql for repository mutations and gh pr create for opening new pull requests.
  • Sanitization: No sanitization or validation of the PR data is mentioned before processing.
  • [COMMAND_EXECUTION]: The skill uses the gh CLI for various operations.
  • Evidence: It calls gh api graphql for resolving review threads and gh pr create for automating pull request creation.
  • [EXTERNAL_DOWNLOADS]: The skill references an external GitHub repository for implementation patterns.
  • Evidence: References the github/awesome-copilot repository in SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 05:26 AM