Restore working context saved earlier by /context-save. (gstack)
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The workflow reads local Claude Code session transcripts (`~/.claude/projects/`) and GitHub issues/PRs via `gh issue list`, which can ingest outsider-authored free text from external issue submissions.
garrytan/gstack
f0cd9f8
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.