load-github-action-thread

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on shell commands to interact with the environment and GitHub API. It uses the GitHub CLI (gh) to view issues, list runs, and fetch logs. It also executes a local shell script ./agents/scripts/load-github-action-thread.sh which performs the core logic of downloading and importing thread history.
  • [EXTERNAL_DOWNLOADS]: The skill is designed to download artifacts from GitHub Actions. According to the instructions, it fetches codex-thread-* artifacts from workflow runs. These downloads are performed from GitHub, which is an established and trusted service for this developer workflow.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted data from GitHub issue titles, pull request metadata, and workflow logs. However, the provided examples demonstrate safe practices, such as using jaq with the --arg flag to pass external data as variables rather than interpolating them directly into filter strings. The potential risk is considered low given the developer-centric use case and the use of standard CLI tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 06:41 PM