context-save
Save working context. Captures git state, decisions made, and remaining work so any future session can pick up without losing a beat. Use when asked to "save progress", "save state", "context save", or "save my work". Pair with /context-restore to resume later. Formerly /checkpoint — renamed because Claude Code treats /checkpoint as a native rewind alias in current environments, which was shadowing this skill. (gstack)
Security
2 findings — 1 critical severity, 1 medium severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E004: Prompt injection detected in skill instructions
What this means
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
Why it was flagged
Potential prompt injection detected (high risk: 0.85). The skill contains many visible but out-of-scope control instructions (telemetry/brain sync that can publish/session-exfiltrate data, prompts that append/commit CLAUDE.md, git rm vendored code, run upgrade/team-init, auto-config changes, etc.) that go well beyond "save working context" and could change repository state or exfiltrate data, so it effectively hides deceptive capability expansion under the guise of a context-save skill.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
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.
Why it was flagged
Third-party content exposure detected (high risk: 0.70). The skill's GBrain/brain-sync flow (reading ~/.gstack-brain-remote.txt, invoking gstack-brain-sync and running git fetch/merge in GSTACK_HOME) and the Lake Intro "open https://garryslist.org/…" path can pull/visit user-configured remote repositories or public URLs, meaning the agent may ingest untrusted, user-generated third-party content and then use it to influence suggestions or next actions.
- Repository
- garrytan/gstack
- Commit
db9447c
- Audited
- Security analysis
Is this your skill?
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.