Daily Edition Sources +4

Om Patel's Gemini Patch Kept Skills In Their Folder

A June 15 Gemini CLI fix turns a convenience feature, installing community skills, into a tested filesystem boundary.

A rough zine-style Diagram Punk poster showing a community skill card kept inside a .gemini/skills folder by test cards and a prevention patch caveat.
Diagram Punkextensible skills still need folder guards.
repo google-gemini/gemini-cli evidence
4 source signals 1 repo commit bca5667
Evidence: commit bca5667 / June 16, 2026 / Daily Edition
Open Edition Evidence below

Om Patel's June 15 commit to google-gemini/gemini-cli is small enough to read as maintenance, but its subject is a trust question: when users install a skill, where is the code allowed to land?

The patch, bca5667, changes packages/cli/src/utils/skillUtils.ts so install and link targets are resolved inside the skills directory before copying or symlinking. It rejects traversal-style subpaths and invalid skill names instead of letting path math decide the boundary.

The Human Work

The visible work is not just the guard. The tests read like a checklist from someone closing the escape hatches: .., ., empty names, sibling-directory removal, archive subpaths that leave the temp directory, absolute path names, and traversal names with spaces.

That makes this a maintainer story as much as a security story. Skill systems invite users to bring outside instructions into an agent runtime. Patel's patch says that invitation still needs a hard local folder boundary.

Why It Matters

For agent builders, skill installation is a tempting place to optimize for convenience. The Gemini CLI patch shows the maintenance burden behind that choice: if a skill can be installed from a Git source or archive, the installer also has to defend the destination.

The fair follow-up question for the Gemini CLI thread is practical: was this mainly local filesystem hygiene, or preparation for a larger skill ecosystem where remote sources become routine?

Limits

The evidence does not show an exploited incident, and the article should not imply one. It shows a public prevention patch, a contributor-visible review artifact, and tests that make the boundary harder to regress.

Evidence Trail

Receipts below the story

The article above is the public narrative. This section keeps the source trail, limits, and reporting notes on the same page.

Edition
DateJune 16, 2026
LaneDaily Edition
Confidence78%
Sources4
Reposgoogle-gemini/gemini-cli

Reporter Notes

  • The commit's author line is public Git metadata. The article uses only the visible professional contribution and does not infer identity beyond the public name.
  • The tests are the emotional center of the story: they show the contributor closing several path escape routes, not merely changing one helper.
  • The companion works best beside the lead because it turns the same boundary theme into a human maintenance arc.

Primary Evidence

Evidence Limits

  • The evidence does not show an exploited incident, a private security report, or the contributor's personal motivation.
  • The article uses only public professional activity from the commit, public source files, and public PR route.
  • The fair follow-up question is framed as an editorial question, not as a claim about Google's roadmap.
Letters & Corrections

Send a note to the desk

Corrections, missing context, or a follow-up lead.